Source:

Mariusz Šapczyński, Cracow University of Economics, Poland, lapczynm '@' uek.krakow.pl Sylwester Białowąs, Poznan University of Economics and Business, Poland, sylwester.bialowas '@' ue.poznan.pl

Data Set Information:

The dataset contains information on clickstream from online store offering clothing for pregnant women. Data are from five months of 2008 and include, among others, product category, location of the photo on the page, country of origin of the IP address and product price in US dollars.

Attribute Information:

The dataset contains 14 variables described in a separate file (See 'Data set description')

Relevant Papers:

N/A

Citation Request:

If you use this dataset, please cite:

Šapczyński M., Białowąs S. (2013) Discovering Patterns of Users' Behaviour in an E-shop - Comparison of Consumer Buying Behaviours in Poland and Other European Countries, “Studia Ekonomiczne†, nr 151, “La société de l'information : perspective européenne et globale : les usages et les risques d'Internet pour les citoyens et les consommateurs†, p. 144-153

Data description ìe-shop clothing 2008î

Variables:

1. YEAR (2008)

========================================================

2. MONTH -> from April (4) to August (8)

========================================================

3. DAY -> day number of the month

========================================================

4. ORDER -> sequence of clicks during one session

========================================================

5. COUNTRY -> variable indicating the country of origin of the IP address with the

following categories:

1-Australia 2-Austria 3-Belgium 4-British Virgin Islands 5-Cayman Islands 6-Christmas Island 7-Croatia 8-Cyprus 9-Czech Republic 10-Denmark 11-Estonia 12-unidentified 13-Faroe Islands 14-Finland 15-France 16-Germany 17-Greece 18-Hungary 19-Iceland 20-India 21-Ireland 22-Italy 23-Latvia 24-Lithuania 25-Luxembourg 26-Mexico 27-Netherlands 28-Norway 29-Poland 30-Portugal 31-Romania 32-Russia 33-San Marino 34-Slovakia 35-Slovenia 36-Spain 37-Sweden 38-Switzerland 39-Ukraine 40-United Arab Emirates 41-United Kingdom 42-USA 43-biz (.biz) 44-com (.com) 45-int (.int) 46-net (.net) 47-org (*.org)

========================================================

6. SESSION ID -> variable indicating session id (short record)

========================================================

7. PAGE 1 (MAIN CATEGORY) -> concerns the main product category:

1-trousers 2-skirts 3-blouses 4-sale

========================================================

8. PAGE 2 (CLOTHING MODEL) -> contains information about the code for each product

(217 products)

========================================================

9. COLOUR -> colour of product

1-beige 2-black 3-blue 4-brown 5-burgundy 6-gray 7-green 8-navy blue 9-of many colors 10-olive 11-pink 12-red 13-violet 14-white

========================================================

10. LOCATION -> photo location on the page, the screen has been divided into six parts:

1-top left 2-top in the middle 3-top right 4-bottom left 5-bottom in the middle 6-bottom right

========================================================

11. MODEL PHOTOGRAPHY -> variable with two categories:

1-en face 2-profile

========================================================

12. PRICE -> price in US dollars

========================================================

13. PRICE 2 -> variable informing whether the price of a particular product is higher than

the average price for the entire product category

1-yes 2-no

========================================================

14. PAGE -> page number within the e-store website (from 1 to 5)

++++++++++++++++++++++++++++++++++++++++++++++++++++++++

Unlock the Power of Behavioural Data with GDPR-Compliant Clickstream Insights.

Swash clickstream data offers a comprehensive and GDPR-compliant dataset sourced from users worldwide, encompassing both desktop and mobile browsing behaviour. Here's an in-depth look at what sets us apart and how our data can benefit your organisation.

User-Centric Approach: Unlike traditional data collection methods, we take a user-centric approach by rewarding users for the data they willingly provide. This unique methodology ensures transparent data collection practices, encourages user participation, and establishes trust between data providers and consumers.

Wide Coverage and Varied Categories: Our clickstream data covers diverse categories, including search, shopping, and URL visits. Whether you are interested in understanding user preferences in e-commerce, analysing search behaviour across different industries, or tracking website visits, our data provides a rich and multi-dimensional view of user activities.

GDPR Compliance and Privacy: We prioritise data privacy and strictly adhere to GDPR guidelines. Our data collection methods are fully compliant, ensuring the protection of user identities and personal information. You can confidently leverage our clickstream data without compromising privacy or facing regulatory challenges.

Market Intelligence and Consumer Behaviuor: Gain deep insights into market intelligence and consumer behaviour using our clickstream data. Understand trends, preferences, and user behaviour patterns by analysing the comprehensive user-level, time-stamped raw or processed data feed. Uncover valuable information about user journeys, search funnels, and paths to purchase to enhance your marketing strategies and drive business growth.

High-Frequency Updates and Consistency: We provide high-frequency updates and consistent user participation, offering both historical data and ongoing daily delivery. This ensures you have access to up-to-date insights and a continuous data feed for comprehensive analysis. Our reliable and consistent data empowers you to make accurate and timely decisions.

Custom Reporting and Analysis: We understand that every organisation has unique requirements. That's why we offer customisable reporting options, allowing you to tailor the analysis and reporting of clickstream data to your specific needs. Whether you need detailed metrics, visualisations, or in-depth analytics, we provide the flexibility to meet your reporting requirements.

Data Quality and Credibility: We take data quality seriously. Our data sourcing practices are designed to ensure responsible and reliable data collection. We implement rigorous data cleaning, validation, and verification processes, guaranteeing the accuracy and reliability of our clickstream data. You can confidently rely on our data to drive your decision-making processes.

This dataset provides simulated data for user interactions on an e-commerce platform. It includes sequences of events such as page views, clicks, product views, and purchases. Each record captures user activity within sessions, making it suitable for analyzing clickstream paths and transaction sequences.

Features:

UserID: Unique identifier for each user. SessionID: Unique identifier for each session. Timestamp: Date and time of the interaction. EventType: Type of event (e.g., page view, click, product view, add to cart, purchase). ProductID: Unique identifier for products involved in interactions. Amount: Amount of the transaction (for purchases). Outcome: Target event (e.g., purchase).

This dataset can be used to discover patterns and sequences leading to specific outcomes such as product purchases or churn.

Discover the booming clickstream analytics market! Our in-depth analysis reveals a $948M market in 2025, projected to exceed $3B by 2033 with a 12.8% CAGR. Learn about key drivers, trends, and leading companies shaping this dynamic industry. Get your free market report now!

Snapshot img { margin: 10px !important; } Overview of the global clickstream analytics market

Research analysis on the global clickstream analytics market identifies that benefits such as the availability of detailed customer segmentation will be one of the major factors that will have a positive impact on the growth of the market. A detailed segmentation of the customers will help businesses customize their offerings according to the services and advertisements that a customer prefers. This will provide a better quality of user interaction, will increase conversion rates, and lead to high customer loyalty. Clickstream analytics will provide the necessary data, which, when used on mapping or predictive models, allows for detailed customer segmentation. Technavio’s market research analysts predict that this market will grow at a CAGR of almost 14% by 2021.

In terms of geography, Americas accounted for the major shares of the clickstream analytics market during 2016. The growth in the penetration of the Internet is major factor driving the clickstream analytics market growth in this region. The access to large amounts of data gives businesses a higher chance of monetizing their advertisements with clickstream data. The demand of clickstream analytics will continue to increase in the region with the rise in accuracy of the data and rise in user registrations.

Competitive landscape and key vendors

This market appears to be highly fragmented, owing to the presence of numerous vendors. According to the clickstream analytics market outlook, the increasing adoption of clickstream analytics will increase the number of vendors who enter the market, which in turn, will intensify the level of competition among the players. Though the competition is intense among the players in the developed markets such as North America and Europe, the rising adoption of clickstream analytics in the emerging markets will strengthen the competitive environment among the players in these regions as well.

The leading vendors in the market are -

Google
IBM
Microsoft
Oracle

The other prominent vendors in the market are Adobe Systems, AT INTERNET, SAP, Splunk, Talend, Verto Analytics, Vlocity, and webtrends.

Segmentation by data type and analysis of the clickstream analytics market

Master
Transaction

Master data is mainly essential in e-commerce platforms since it provides vendors with information on the kind of customers who refer the website or customer segments that are interested in buying certain products. During 2016, the master data segment accounted for major shares of the clickstream analytics market. It has been expected that the clickstream analytics market size & share will grow in the forthcoming years.

Segmentation by source and analysis of the clickstream analytics market

Host server
Third- party agreements
Network topology
Tracking host computer

Based on the clickstream analytics market forecast, the host server segment accounted for major share of this market during 2016. When a user requests a web page, the server records information such as the user’s IP address, history of URLs visited, and the type of browser in the server log. Organizations are entering into partnerships with companies that provide products to analyze these logs. They are also partnering with companies that provide consulting services to process clickstream data and aggregate them with e-mail data or online sales data to have a comprehensive view of their clients.

Key questions answered in the report include

What will the market size and the growth rate be in 2021?
What are the key factors driving the global clickstream analytics market?
What are the key market trends impacting the growth of the global clickstream analytics market?
What are the challenges to market growth?
Who are the key vendors in the global clickstream analytics market?
What are the market opportunities and threats faced by the vendors in the global clickstream analytics market?
Trending factors influencing the market shares of the Americas, APAC, and EMEA.
What are the key outcomes of the five forces analysis of the global clickstream analytics market? 

Technavio also offers customization on reports based on specific client requirement.

Clickstream Analytics Market size was valued at USD 1.62 Billion in 2024 and is projected to reach USD 5.3 Billion by 2031, growing at a CAGR of 15.95% from 2024 to 2031.

Global Clickstream Analytics Market Drivers

Growing E-commerce Industry: Adobe Analytics reports that companies using clickstream analytics saw an average increase of 23% in conversion rates and a 15% reduction in cart abandonment rates in 2021. Increasing online shopping drives the need for clickstream analytics to enhance user experience and optimize conversion rates. Rising Focus on Customer Personalization: According to the Interactive Advertising Bureau (IAB), digital advertising spending reached $189 billion in 2021, a 35.4% increase from 2020, with companies investing heavily in analytics to optimize their campaigns. Businesses are adopting clickstream analytics to provide personalized product recommendations and targeted marketing campaigns. Advancements in AI and Machine Learning: According to Gartner, organizations that have implemented real-time analytics reported a 30% increase in customer satisfaction scores. Integration with AI technologies helps in predictive analysis, enabling businesses to forecast user behavior and trends.

Clickstream Anomaly Detection AI Market Outlook

According to our latest research, the global Clickstream Anomaly Detection AI market size reached USD 1.57 billion in 2024, reflecting a robust demand for advanced analytics in digital behavior monitoring. The market is poised for significant expansion, expected to grow at a CAGR of 18.9% from 2025 to 2033. By the end of the forecast period, the market is projected to attain a value of USD 7.59 billion by 2033. This remarkable growth is driven by the increasing necessity for real-time fraud detection, digital marketing optimization, and personalized customer engagement across multiple industries. As per our latest research, organizations are rapidly adopting AI-powered clickstream anomaly detection solutions to enhance security, optimize user experiences, and gain actionable insights from vast volumes of digital data.

The primary growth factor fueling the Clickstream Anomaly Detection AI market is the exponential rise in digital transactions and online interactions. As businesses shift towards digital-first strategies, the volume of clickstream data generated from websites, mobile applications, and digital platforms has surged. This data is invaluable for understanding user behavior, but it also presents significant challenges in terms of data management and anomaly detection. AI-powered solutions are uniquely positioned to analyze large datasets in real time, identifying unusual patterns that may indicate fraudulent activity, system errors, or opportunities for optimization. The increasing sophistication of cyber threats and the need for proactive security measures further amplify the demand for advanced anomaly detection capabilities, making AI-driven clickstream analysis a critical component of modern digital infrastructure.

Another significant driver of market growth is the growing emphasis on personalized customer experiences and targeted marketing. In highly competitive sectors such as e-commerce, financial services, and media, organizations leverage clickstream data to tailor content, offers, and recommendations to individual users. AI-based anomaly detection tools enable businesses to identify deviations from normal user journeys, uncovering hidden opportunities for engagement and conversion. This not only enhances customer satisfaction but also improves operational efficiency by automating the detection of irregularities that would otherwise go unnoticed. The integration of AI with clickstream analytics platforms is enabling a new era of data-driven decision-making, where businesses can respond swiftly to emerging trends and customer preferences.

Regulatory compliance and data privacy concerns are also shaping the evolution of the Clickstream Anomaly Detection AI market. With stringent data protection laws such as GDPR and CCPA, organizations are under increasing pressure to ensure the integrity and security of user data. AI-powered anomaly detection systems provide an essential layer of defense by continuously monitoring clickstream activity for signs of data breaches, unauthorized access, or suspicious behavior. This capability not only helps organizations meet regulatory requirements but also builds trust with customers and stakeholders. As regulatory frameworks continue to evolve, the demand for compliant and transparent AI-driven analytics solutions is expected to rise, further propelling market growth.

From a regional perspective, North America currently dominates the Clickstream Anomaly Detection AI market, accounting for the largest share in 2024. This leadership is attributed to the high adoption of advanced analytics technologies, a mature digital ecosystem, and the presence of major industry players. However, the Asia Pacific region is anticipated to exhibit the fastest growth over the forecast period, driven by rapid digitalization, expanding e-commerce markets, and increasing investments in AI infrastructure. Europe also represents a significant market, supported by strong regulatory frameworks and a focus on data-driven innovation. As organizations worldwide continue to embrace digital transformation, the demand for sophisticated clickstream anomaly detection solutions is expected to accelerate across all major regions.

Datasys Referral Pathways reveal the digital journeys consumers take online by tracking over 50M daily referral URLs. This dataset shows which platforms, domains, and publishers drive traffic, offering insights into acquisition sources, user navigation patterns, and competitive performance. It helps marketers identify the strongest channels for customer engagement and optimize web strategies.

Clickstream Anomaly Detection AI Market Outlook

As per the latest research, the global Clickstream Anomaly Detection AI market size stood at USD 1.34 billion in 2024 and is projected to reach USD 7.98 billion by 2033, expanding at a robust CAGR of 21.7% over the forecast period. The market’s remarkable growth is primarily driven by the increasing need for advanced analytics to identify fraudulent activities and optimize user experiences across digital platforms. The surge in online transactions, coupled with the proliferation of e-commerce and digital financial services, is fueling the demand for sophisticated anomaly detection solutions powered by artificial intelligence.

The rapid digital transformation across industries is a primary growth catalyst for the Clickstream Anomaly Detection AI market. Organizations are increasingly leveraging digital channels to engage customers, leading to an exponential rise in clickstream data volumes. This data, which captures every digital interaction, provides valuable insights but also presents challenges in detecting outliers that may signal fraud, system failures, or user behavior shifts. AI-driven anomaly detection tools are becoming indispensable as they enable real-time monitoring and rapid identification of deviations from normal patterns, thereby enhancing operational efficiency, reducing risk, and improving customer satisfaction. The adoption of these tools is further propelled by the growing awareness of the financial and reputational damage caused by undetected anomalies in clickstream data.

Another significant growth factor is the technological advancement in AI and machine learning algorithms, which now offer unparalleled accuracy and scalability in anomaly detection. Modern AI models can process vast and complex datasets in real time, learning from evolving patterns to continuously improve detection rates. This technological evolution is particularly relevant for sectors such as e-commerce, financial services, and healthcare, where user behavior is dynamic and the cost of missed anomalies can be substantial. Additionally, the integration of clickstream anomaly detection with broader analytics and cybersecurity solutions is creating a holistic approach to data integrity and security, further driving market adoption among enterprises seeking comprehensive digital risk management.

Regulatory compliance and data privacy requirements are also shaping the growth trajectory of the Clickstream Anomaly Detection AI market. As regulations such as GDPR, CCPA, and industry-specific mandates become more stringent, organizations are under pressure to monitor and secure digital interactions proactively. AI-powered anomaly detection systems help businesses not only comply with these regulations by identifying suspicious or unauthorized activities but also build trust with customers by safeguarding their digital journeys. This dual benefit of compliance and customer trust is prompting investments in advanced clickstream analytics, particularly in highly regulated sectors like banking, healthcare, and telecommunications.

From a regional perspective, North America currently dominates the Clickstream Anomaly Detection AI market, accounting for the largest revenue share in 2024, driven by the presence of leading technology providers and high digital adoption rates. However, Asia Pacific is expected to exhibit the fastest growth during the forecast period, fueled by rapid digitalization, expanding e-commerce ecosystems, and increasing investments in AI-driven analytics across emerging economies such as China and India. Europe also holds a significant market share, supported by robust regulatory frameworks and a strong focus on data privacy. Latin America and the Middle East & Africa are witnessing steady growth as organizations in these regions embrace digital transformation and seek to enhance their cybersecurity and analytics capabilities.

Component Analysis

The Clickstream Anomaly Detection AI market is segmented by component into Software and Services, each playing a pivotal role in the ecosystem. The software segment encompasses AI-powered platforms and tools designed to analyze clickstream data, identify anomalies, and deliver actionable insights in real time. These solutions leverage advanced machine learning algorithms, deep learning models, and natural language processing to detect subtle deviations in user behavior patterns, making them highl

This project contains data sets containing counts of (referer, resource) pairs extracted from the request logs of Wikipedia. A referer is an HTTP header field that identifies the address of the webpage that linked to the resource being requested. The data shows how people get to a Wikipedia article and what links they click on. In other words, it gives a weighted network of articles, where each edge weight corresponds to how often people navigate from one page to another. To give an example, consider the figure below, which shows incoming and outgoing traffic to the "London" article on English Wikipedia during January 2015.

https://upload.wikimedia.org/wikipedia/commons/0/02/London_clickstream.png%20=300x100" alt="Alt text">

Official Documentation

Can be found here

Synthetic Clickstream Generation Market Outlook

According to our latest research, the Global Synthetic Clickstream Generation market size was valued at $1.1 billion in 2024 and is projected to reach $5.4 billion by 2033, expanding at a robust CAGR of 18.7% during 2024–2033. The primary driver for the rapid expansion of this market is the surging demand for high-quality, privacy-compliant behavioral data to power advanced analytics, AI training, and digital optimization across industries. As organizations accelerate their digital transformation journeys, the need for scalable, synthetic data that mimics real user journeys without compromising sensitive information has become paramount. This trend is especially pronounced in sectors where regulatory scrutiny and data privacy concerns restrict the use of genuine clickstream data, making synthetic alternatives an indispensable asset for innovation and compliance.

Regional Outlook

North America currently dominates the Synthetic Clickstream Generation market, accounting for over 38% of the global market share in 2024. This leadership is attributed to the region’s mature digital ecosystem, a high concentration of technology innovators, and a strong focus on data-driven decision-making across enterprises. The presence of leading cloud service providers, robust digital advertising industries, and stringent privacy regulations such as CCPA and HIPAA have accelerated the adoption of synthetic clickstream solutions. Furthermore, North American enterprises are early adopters of AI and machine learning, leveraging synthetic data to enhance model robustness while safeguarding user privacy. The region’s established regulatory frameworks and continued investment in R&D further reinforce its position as the largest market for synthetic clickstream generation.

The Asia Pacific region is emerging as the fastest-growing market, projected to register a remarkable CAGR of 22.5% from 2024 to 2033. Rapid digitalization, the proliferation of e-commerce platforms, and increasing investments in artificial intelligence and analytics are key drivers fueling market expansion in countries such as China, India, Japan, and South Korea. Enterprises in Asia Pacific are increasingly leveraging synthetic clickstream data to optimize user experiences, detect fraud, and personalize digital offerings. The region’s vibrant start-up ecosystem, coupled with government initiatives promoting digital transformation and data security, further accelerates adoption. As digital penetration deepens and regulatory requirements evolve, Asia Pacific is poised to become a critical growth engine for the global synthetic clickstream generation market.

Emerging economies in Latin America and Middle East & Africa are witnessing steady adoption of synthetic clickstream generation solutions, albeit from a lower base. Challenges such as limited digital infrastructure, lower awareness, and evolving regulatory landscapes can temper growth in these regions. However, localized demand from sectors like fintech, digital advertising, and healthcare is gradually increasing, driven by the need to comply with privacy norms and support digital innovation. Governments are beginning to implement data protection policies, which, while initially posing compliance challenges, are likely to drive long-term adoption of synthetic data solutions. As awareness spreads and technology becomes more accessible, these regions offer significant untapped potential for market players seeking global expansion.

Report Scope

We view web forums as virtual living organisms feeding on user's clicks and investigate how they grow at the expense of clickstreams. We find that (the number of page views in a given time period) and (the number of unique visitors in the time period) of the studied forums satisfy the law of the allometric growth, i.e., . We construct clickstream networks and explain the observed temporal dynamics of networks by the interactions between nodes. We describe the transportation of clickstreams using the function , in which is the total amount of clickstreams passing through node and is the amount of the clickstreams dissipated from to the environment. It turns out that , an indicator for the efficiency of network dissipation, not only negatively correlates with , but also sets the bounds for . In particular, when and when . Our findings have practical consequences. For example, can be used as a measure of the “stickiness” of forums, which quantifies the stable ability of forums to remain users “lock-in” on the forum. Meanwhile, the correlation between and provides a method to predict the long-term “stickiness” of forums from the clickstream data in a short time period. Finally, we discuss a random walk model that replicates both of the allometric growth and the dissipation function .

Datos brings to market anonymized, at scale, consolidated privacy-secured datasets with a granularity rarely found in the market. Get access to the desktop and mobile browsing behavior for millions of users across the globe, packaged into clean, easy-to-understand data products and reports.

The Datos Activity Feed is an event-level accounting of all observed URL visits executed by devices which Datos has access to over a given period of time.

This feed can be delivered on a daily basis, delivering the previous day’s data. It can be filtered by any of the fields, so you can focus on what’s important for you, whether it be specific markets or domains.

Now available with Datos Low-Latency Feed This add-on ensures delivery of approximately 99% of all devices before markets open in New York (the lowest latency product on the market). Our clickstream data is made up of an array of upstream sources. The DLLF makes the daily output of these sources available as they arrive and are processed, rather than a once-daily batch.

Raising public awareness of sepsis, a potentially life-threatening dysregulated host response to infection, to hasten its recognition has become a major focus of physicians, investigators, and both non-governmental and governmental agencies. While the internet is a common means by which to seek out healthcare information, little is understood about patterns and drivers of these behaviors. We sought to examine traffic to Wikipedia, a popular and publicly available online encyclopedia, to better understand how, when, and why users access information about sepsis. Utilizing pageview traffic data for all available language localizations of the sepsis and septic shock pages between July 1, 2015 and June 30, 2018, significantly outlying daily pageview totals were identified using a seasonal hybrid extreme studentized deviate approach. Consecutive outlying days were aggregated, and a qualitative analysis was undertaken of print and online news media coverage to identify potential correlates. Traffic patterns were further characterized using paired referrer to resource (i.e. clickstream) data, which were available for a temporal subset of the pageviews. Of the 20,557,055 pageviews across 65 linguistic localizations, 47 of the 1,096 total daily pageview counts were identified as upward outliers. After aggregating sequential outlying days, 25 epochs were examined. Qualitative analysis identified at least one major news media correlate for each, which were typically related to high-profile deaths from sepsis and, less commonly, awareness promotion efforts. Clickstream analysis suggests that most sepsis and septic shock Wikipedia pageviews originate from external referrals, namely search engines. Owing to its granular and publicly available traffic data, Wikipedia holds promise as a means by which to better understand global drivers of online sepsis information seeking. Further characterization of user engagement with this information may help to elucidate means by which to optimize the visibility, content, and delivery of awareness promotion efforts.

THIS IS STILL WIP, PLEASE DO NOT CIRCULATE

About This dataset contains counts of (referer, article) pairs extracted from the request logs of English Wikipedia. When a client requests a resource by following a link, the URI of the webpage that linked to the resource is included in the request in an HTTP header called the "referer". This data captures 15 million (referer, article) pairs from a total of 2.3 billion requests collected during a 3-week period (January 8 to January 31, 2015). Data Preparation- The dataset only includes requests to articles in the main namespace of the desktop version of English Wikipedia (see https://en.wikipedia.org/wiki/Wikipedia:Namespace) - Requests to MediaWiki redirects are excluded - Spider traffic was excluded using the ua-parser library (https://github.com/tobie/ua-parser) - Referers were mapped to a fixed set of values corresponding to internal traffic or external traffic from one of the top 5 global traffic sources of English Wikipedia, based on this scheme: - an article in the main namespace of English Wikipedia -> the article title - any Wikipedia page that is not in the main namespace of English Wikipedia -> 'other-wikipedia' - a page from any other Wikimedia project -> 'other-internal' - Google -> 'other-google' - Yahoo -> 'other-yahoo' - Bing -> 'other-bing' - Facebook -> 'other-facebook' - Twitter -> 'other-twitter' - anything else -> 'other' For the exact mapping see https://github.com/ewulczyn/wmf/blob/master/mc/oozie/hive_query.sql#L30-L48 - (referer, article) pairs with less than 10 observations were removed from the dataset - we do not include requests with an empty or ill-formatted referer ApplicationsThis data can be used for various purposes: - determining the most frequent links people click on for a given article- determining the most common links people followed to an article- determining how much of the total traffic to an article clicked on a link in that article- generating a Markov chain over English Wikipedia Format:- prev_id: if the referer does not correspond to an article in the main namespace of English Wikipedia, this value will be empty. Otherwise, it contains the unique MediaWiki page ID of the article corresponding to the referer i.e. the previous article the client was on- curr_id: the MediaWiki unique page ID of the article the client requested- n: the number of occurrences of the '(referer, article)' pair- prev_title: the result of mapping the referer URL to the fixed set of values described above- curr_title: the title of the article the client requested

LicenseAll files included in this datasets are released under CC0: https://creativecommons.org/publicdomain/zero/1.0/ Source codehttps://github.com/ewulczyn/wmf/blob/master/mc/oozie/hive_query.sql (MIT license)

THIS IS WHOLLY INDEPENDENT RESEARCH AND DATA. WE’RE NOT AFFILIATED WITH NETFLIX OR ANY OTHER STREAMING PLATFORM OR STUDIO.

Content

The dataset covers user behaviour on Netflix from users in the UK to opted-in to have their anonymized browsing activity tracked. It only includes desktop and laptop activity (which Netflix estimate is around 25% of global traffic) and is for a fixed window of time (January 2017 to June 2019, inclusive). It documents each time someone in our tracked panel in the UK clicked on a Netflix.com/watch URL for a movie.

'Duration' shows how long it was (in seconds) until that user clicked on another URL. A watch time of zero seconds means they visited the page but instantly clicked away.

Why this data matters

As more of the media economy takes place within restricted private networks, filmmakers and creators are becoming further removed from what audiences want. Without feedback, creators struggle to make commercial projects. Without reliable financial estimates, business plans become fanciful. Without data, we’re all just guessing.

As streaming continues to become an ever-larger window of release, it has drawn an impenetrable veil over a vital part of a film or TV show’s financial journey. This has created an artificial data drought. So much so that our clickstream dataset is currently the only global measure of VOD activity of its kind.

And it’s not perfect. There are limitations and caveats with the dataset which means that we are observing the truth through an imperfect lens. But in the absence of anything better, this is what we’re left to work with.

More on this here https://vodclickstream.com/why-this-matters/

Acknowledgements

We wouldn't be here without the help of others. If you owe any attributions or thanks, include them here along with any citations of past research. This is a community project aimed at helping content creators understand how the new world of streaming affects the demand for their works.

It has taken over a year and countless hours from many people for it to come together. It would not have been possible without the work of Stephen Follows, Dr. José Eliel Camargo-Molina, Jack Tann, Dr. Alejandro Celis, and Victoria Myerscough.

You can read more about our origin story at https://vodclickstream.com/our-origin-story/

Inspiration

We're really excited to see what people can use this data for. Our initial impetus or the project was to help filmmakers get the signals they need to know what to make, how much to spend, and their chances of commercial success. But it can reveal so much more than just that.

This initial dataset is just for movies and just for users in the UK. We also have data on TV shows and comedy specials, extending across all major countries. We will be releasing more soon. Get in touch if there’s data you’re after along these lines https://vodclickstream.com/contact/

Snapshot img

Enterprise Search Market Size 2025-2029

The enterprise search market size is forecast to increase by USD 4.21 billion, at a CAGR of 10.5% between 2024 and 2029.

The market is experiencing significant growth, driven by the increasing penetration of the Internet worldwide and the rise of digital assistants and voice search technologies. These trends reflect the evolving digital landscape, as businesses and organizations seek to optimize their online presence and enhance user experience. However, the market also faces challenges, most notably the growing concern related to cyberattacks. As businesses increasingly rely on digital platforms for information management and retrieval, ensuring the security of enterprise search systems becomes paramount. Improvements in information technology, such as 5G technology and broadband, are also contributing to the growth of the market.
Companies must invest in robust security measures to protect sensitive data and mitigate the risks associated with cyber threats. To capitalize on the opportunities presented by the market and navigate these challenges effectively, organizations should prioritize innovation, invest in advanced technologies, and maintain a strong focus on user experience and security. Artificial Intelligence (AI) and Natural Language Processing (NLP) technologies are revolutionizing search experiences, enabling personalized results and improving user experience.

What will be the Size of the Enterprise Search Market during the forecast period?

Get Key Insights on Market Forecast (PDF) Request Free Sample

The market continues to evolve, driven by advancements in technology and the increasing demand for efficient information access across various sectors. Key components of this dynamic landscape include keyword extraction, search indexing, and information architecture, which enable accurate and relevant results. Boolean search and search analytics provide further refinement, while metadata extraction and data governance ensure data quality. Personalized search, natural language processing, and vector search are transforming the user experience, delivering more precise and contextually relevant results. Knowledge management, relevance ranking, and search filtering further enhance the search process, while semantic search and user behavior analysis provide deeper insights.
Clickstream data and query logs offer valuable information for optimizing search UI and search performance. Document ranking and query understanding are essential for delivering accurate and timely results. Search UI and search performance are crucial factors in user satisfaction, driving the ongoing development of enterprise search solutions. According to recent industry reports, the market is expected to grow by over 15% annually, reflecting the continuous demand for advanced search capabilities and the integration of emerging technologies. For instance, a leading financial services company reported a 25% increase in sales following the implementation of a new enterprise search solution.

How is this Enterprise Search Industry segmented?

The enterprise search industry research report provides comprehensive data (region-wise segment analysis), with forecasts and estimates in 'USD million' for the period 2025-2029, as well as historical data from 2019-2023 for the following segments.

Type

  Local search
  Hosted search


End-user

  Large enterprises
  SMEs


Deployment

  Cloud-based
  On-premises


Geography

  North America

    US
    Canada


  Europe

    France
    Germany
    Italy
    UK


  APAC

    China
    India
    Japan


  South America

    Brazil


  Rest of World (ROW)

By Type Insights

The Local search segment is estimated to witness significant growth during the forecast period. The market in the US is a significant and continually evolving sector, with local search holding a substantial share in 2024. Approximately 60% of all searches performed on Google are local, underlining its importance for businesses aiming to reach their target audience effectively. This trend is expected to persist, as the local search segment is projected to continue its dominance during the forecast period. Local search offers numerous advantages for various industries, including real estate, legal firms, dental clinics, and small businesses. By optimizing a website for a specific geographical area, businesses can attract more targeted traffic and improve online visibility. Deep learning applications, including natural language processing and large language models, are transforming software design patterns, such as microservices architecture and prompt engineering software.

This, in turn, can lead to increased footfall at brick-and-mortar locations and higher online sales. Furthermore, local search helps businesses maintain accurate online directories and citations, ensuring consistent inf

The Open University (OU) dataset is an open database containing student demographic and click-stream interaction with the virtual learning platform. The available data are structured in different CSV files. You can find more information about the original dataset at the following link: https://analyse.kmi.open.ac.uk/open_dataset.

We extracted a subset of the original dataset that focuses on student information. 25,819 records were collected referring to a specific student, course and semester. Each record is described by the following 20 attributes: code_module, code_presentation, gender, highest_education, imd_band, age_band, num_of_prev_attempts, studies_credits, disability, resource, homepage, forum, glossary, outcontent, subpage, url, outcollaborate, quiz, AvgScore, count.

Two target classes were considered, namely Fail and Pass, combining the original four classes (Fail and Withdrawn and Pass and Distinction, respectively). The final_result attribute contains the target values.

All features have been converted to numbers for automatic processing.

Below is the mapping used to convert categorical values to numeric:

code_module: 'AAA'=0, 'BBB'=1, 'CCC'=2, 'DDD'=3, 'EEE'=4, 'FFF'=5, 'GGG'=6

code_presentation: '2013B'=0, '2013J'=1, '2014B'=2, '2014J'=3

gender: 'F'=0, 'M'=1

highest_education: 'No_Formal_quals'=0, 'Post_Graduate_Qualification'=1, 'HE_Qualification'=2, 'Lower_Than_A_Level'=3, 'A_level_or_Equivalent'=4

IMBD_band: 'unknown'=0, 'between_0_and_10_percent'=1, 'between_10_and_20_percent'=2, 'between_20_and_30_percent'=3, 'between_30_and_40_percent'=4, 'between_40_and_50_percent'=5, 'between_50_and_60_percent'=6, 'between_60_and_70_percent'=7, 'between_70_and_80_percent'=8, 'between_80_and_90_percent'=9, 'between_90_and_100_percent'=10

age_band: 'between_0_and_35'=0, 'between_35_and_55'=1, 'higher_than_55'=2

disability: 'N'=0, 'Y'=1

student's outcome: 'Fail'=0, 'Pass'=1

For more detailed information, please refer to:

Casalino G., Castellano G., Vessio G. (2021) Exploiting Time in Adaptive Learning from Educational Data. In: Agrati L.S. et al. (eds) Bridges and Mediation in Higher Distance Education. HELMeTO 2020. Communications in Computer and Information Science, vol 1344. Springer, Cham. https://doi.org/10.1007/978-3-030-67435-9_1

User Session Replay Analysis AI Market Outlook

According to our latest research, the global User Session Replay Analysis AI market size reached USD 1.82 billion in 2024, reflecting robust adoption across digital-first enterprises. The market is experiencing a strong growth trajectory, registering a CAGR of 18.7% during the forecast period. By 2033, the User Session Replay Analysis AI market is projected to reach USD 9.03 billion, fueled by the increasing demand for advanced analytics in digital customer experience and compliance management. The surge in digital transformation initiatives, coupled with the need for actionable insights into user behavior, is a key growth factor propelling this market forward.

The primary growth driver for the User Session Replay Analysis AI market is the exponential increase in digital interactions across industries such as e-commerce, BFSI, and healthcare. Organizations are recognizing the critical importance of understanding user journeys in granular detail to optimize website performance, improve conversion rates, and enhance customer experience. The use of AI-powered session replay tools enables businesses to capture, visualize, and analyze every user interaction, offering invaluable insights that go beyond traditional analytics. This capability is especially vital as businesses strive to reduce customer churn, personalize digital experiences, and maintain a competitive edge in an increasingly crowded digital marketplace.

Another significant factor fueling market growth is the rising emphasis on compliance and risk management in regulated industries. With the proliferation of data privacy regulations such as GDPR, CCPA, and HIPAA, enterprises are leveraging session replay analysis AI to monitor, audit, and document user interactions for compliance purposes. These solutions offer advanced features like automated anomaly detection, real-time alerts, and secure data handling, helping organizations mitigate the risk of non-compliance and potential legal repercussions. As regulatory frameworks continue to evolve, the demand for AI-driven session replay solutions that can seamlessly align with compliance mandates is expected to intensify, further boosting market expansion.

Technological advancements in AI and machine learning are also playing a pivotal role in the evolution of the User Session Replay Analysis AI market. Modern solutions now incorporate sophisticated algorithms capable of identifying user frustration signals, predicting abandonment, and providing prescriptive recommendations for UX improvements. The integration of AI with session replay analytics is enabling real-time decision-making and automation, reducing the manual effort required for analysis and accelerating the implementation of optimizations. This trend is particularly pronounced among large enterprises and digitally native organizations, which are increasingly investing in scalable, AI-powered analytics platforms to drive business outcomes.

From a regional perspective, North America continues to dominate the User Session Replay Analysis AI market, accounting for the largest revenue share in 2024. The region’s leadership can be attributed to the high digital maturity of enterprises, early adoption of advanced analytics, and stringent compliance requirements. However, Asia Pacific is witnessing the fastest growth, driven by rapid digitalization, expanding e-commerce sectors, and increasing awareness of customer experience optimization. Europe maintains a strong presence, particularly in regulated industries such as BFSI and healthcare, while Latin America and the Middle East & Africa are emerging as promising markets due to growing investments in digital infrastructure and analytics technologies.

Component Analysis

The User Session Replay Analysis AI market is segmented by component into software and services, each playing a distinct yet complementary role in the ecosystem. The software segment dominates the market, accounting for the largest share in 2024, as enterprises increasingly adopt AI-powered platforms to capture, replay, and analyze user sessions across digital channels. These platforms offer a comprehensive suite of features, including heatmaps, clickstream analysis, funnel visualization, and anomaly detection, empowering organizations to gain deep insights into user behavior and identify friction points in real time. The growing integration of AI and machine learning capabilities into session replay softw

Snapshot img

Retail Analytics Market Size 2025-2029

The retail analytics market size is forecast to increase by USD 28.47 billion, at a CAGR of 29.5% between 2024 and 2029.

The market is experiencing significant growth, driven by the increasing volume and complexity of data generated by retail businesses. This data deluge offers valuable insights for retailers, enabling them to optimize operations, enhance customer experience, and make data-driven decisions. However, this trend also presents challenges. One of the most pressing issues is the increasing adoption of Artificial Intelligence (AI) in the retail sector. While AI brings numerous benefits, such as personalized marketing and improved supply chain management, it also raises privacy and security concerns among customers.
Retailers must address these concerns through transparent data handling practices and robust security measures to maintain customer trust and loyalty. Navigating these challenges requires a strategic approach, with a focus on data security, customer privacy, and effective implementation of AI technologies. Companies that successfully harness the power of retail analytics while addressing these challenges will gain a competitive edge in the market.

What will be the Size of the Retail Analytics Market during the forecast period?

Explore in-depth regional segment analysis with market size data - historical 2019-2023 and forecasts 2025-2029 - in the full report.
Request Free Sample

The market continues to evolve, driven by the constant need for businesses to gain insights from their data and adapt to shifting consumer behaviors. Entities such as text analytics, data quality, price optimization, customer journey mapping, mobile analytics, time series analysis, regression analysis, social media analytics, data mining, historical data analysis, and data cleansing are integral components of this dynamic landscape. Text analytics uncovers hidden patterns and trends in unstructured data, while data quality ensures the accuracy and consistency of information. Price optimization leverages historical data to determine optimal pricing strategies, and customer journey mapping provides insights into the customer experience.

Mobile analytics caters to the growing number of mobile shoppers, and time series analysis identifies trends and patterns over time. Regression analysis uncovers relationships between variables, social media analytics monitors brand sentiment, and data mining uncovers hidden patterns and correlations. Historical data analysis informs strategic decision-making, and data cleansing prepares data for analysis. Customer feedback analysis provides valuable insights into customer satisfaction, and association rule mining uncovers relationships between customer behaviors and purchases. Predictive analytics anticipates future trends, real-time analytics delivers insights in real-time, and market basket analysis uncovers relationships between products. Data security safeguards sensitive information, machine learning (ML) and artificial intelligence (AI) enhance data analysis capabilities, and cloud-based analytics offers flexibility and scalability.

Business intelligence (BI) and open-source analytics provide comprehensive data analysis solutions, while inventory management and supply chain optimization streamline operations. Data governance ensures data is used ethically and effectively, and loyalty programs and A/B testing optimize customer engagement and retention. Seasonality analysis accounts for seasonal trends, and trend analysis identifies emerging trends. Data integration connects disparate data sources, and clickstream analysis tracks user behavior on websites. In the ever-changing retail landscape, these entities are seamlessly integrated into retail analytics solutions, enabling businesses to stay competitive and adapt to evolving market dynamics.

How is this Retail Analytics Industry segmented?

The retail analytics industry research report provides comprehensive data (region-wise segment analysis), with forecasts and estimates in 'USD million' for the period 2025-2029, as well as historical data from 2019-2023 for the following segments.

Application

  In-store operation
  Customer management
  Supply chain management
  Marketing and merchandizing
  Others


Component

  Software
  Services


Deployment

  Cloud-based
  On-premises


Geography

  North America

    US
    Canada


  Europe

    France
    Germany
    Italy
    UK


  APAC

    China
    India
    Japan
    South Korea


  Rest of World (ROW)

By Application Insights

The in-store operation segment is estimated to witness significant growth during the forecast period. In the realm of retail, the in-store operation segment of the market plays a pivotal role in optimizing brick-and-mortar retail operations. This segment encompasses various data analytics applications within phys