This dataset includes the analysis year inputs and outputs from the Air Quality Conformity Analysis approved in June 2025. The horizon year is 2050 and reflects the policies and projects adopted in the ON TO 2050 Regional Comprehensive Plan.The air quality analysis is completed twice annually, in the second quarter and the fourth quarter. The data associated with the analysis is named based on the year the analysis was completed and the quarter it was completed. Therefore, the files in this dataset are referred to as c25q2 data.The analysis years for this conformity cycle include 2019, 2025, 2030, 2035, 2040, and 2050. We associate scenario numbers with the analysis years as shown below. You will notice the scenario numbers 100–700 referenced in many of the filenames or in headers within the files.Analysis year scenario numbers:2019 | 1002025 | 2002030 | 3002035 | 4002040 | 5002050 | 700 Links to download data files:Travel Demand Model Data (c25q2) - 2019 BaseTravel Demand Model Data (c25q2) - 2025 ForecastTravel Demand Model Data (c25q2) - 2030 ForecastTravel Demand Model Data (c25q2) - 2035 ForecastTravel Demand Model Data (c25q2) - 2040 ForecastTravel Demand Model Data (c25q2) - 2050 Forecast For additional information, see the travel demand model documentation.

Marketing Mix Modeling for Travel Market Outlook

According to our latest research, the global marketing mix modeling for travel market size reached USD 1.32 billion in 2024, driven by the increasing adoption of data-driven decision-making in the travel industry. The market is expected to grow at a robust CAGR of 13.2% from 2025 to 2033, reaching a forecasted market value of USD 3.74 billion by 2033. This growth is primarily fueled by the rising need among travel businesses to optimize marketing spend and enhance customer engagement through sophisticated analytics and modeling techniques.

One of the key growth factors for the marketing mix modeling for travel market is the escalating competition within the global travel and tourism sector. As travel companies, including airlines, hotels, and online travel agencies, strive to capture a larger share of the market, they are increasingly turning to advanced analytics to understand the effectiveness of their marketing strategies. Marketing mix modeling enables these organizations to measure the impact of various marketing channels, such as digital, print, and broadcast media, on bookings and revenue. By leveraging these insights, travel businesses can allocate their marketing budgets more efficiently, resulting in improved return on investment (ROI) and enhanced campaign performance. The growing emphasis on personalization and targeted marketing further amplifies the demand for robust modeling solutions, as travel companies seek to deliver relevant offers to specific customer segments.

In addition to competitive pressures, the proliferation of digital touchpoints and the growing complexity of the customer journey are significant drivers of market growth. The modern traveler interacts with brands across multiple platforms—websites, mobile apps, social media, and third-party aggregators—making it increasingly challenging to track and attribute the impact of different marketing activities. Marketing mix modeling provides a holistic view of the customer journey by integrating data from various sources, enabling travel companies to identify the most influential touchpoints and optimize their marketing strategies accordingly. The adoption of cloud-based solutions and advancements in machine learning and artificial intelligence have further enhanced the scalability and accuracy of marketing mix models, making them accessible to organizations of all sizes within the travel industry.

Another important growth factor is the rapid digital transformation occurring within the travel sector. As travel companies invest in digital infrastructure and embrace technologies such as big data analytics, artificial intelligence, and cloud computing, the volume and granularity of data available for analysis have increased exponentially. This wealth of data allows for more precise modeling and forecasting of marketing outcomes, empowering travel businesses to make data-driven decisions in real time. Furthermore, the integration of external data sources, such as economic indicators, weather patterns, and competitor activities, into marketing mix models offers a more comprehensive understanding of market dynamics, enabling travel companies to respond proactively to changing conditions and capitalize on emerging opportunities.

From a regional perspective, North America and Europe currently account for the largest shares of the global marketing mix modeling for travel market, owing to the high concentration of travel companies and the widespread adoption of advanced analytics solutions. However, the Asia Pacific region is expected to exhibit the fastest growth over the forecast period, driven by the rapid expansion of the travel and tourism industry, increasing digitalization, and rising investments in marketing technologies. Latin America and the Middle East & Africa are also witnessing steady growth, supported by improving internet penetration and the emergence of new travel destinations. As travel companies across all regions seek to enhance their marketing effectiveness and adapt to evolving consumer preferences, the demand for marketing mix modeling solutions is poised to rise significantly in the coming years.

Component Analysis

The marketing mix modeling for travel market is segmented by component into software and services. The software segment encompasses a wide range of analytics platforms and modeling tools that enable travel companies to process large volumes of marketing data, build predic

Great Smoky Mountains National Park Travel Time: This reference is for 3 travel time model rasters, with time from Park Headquarters, Twin Creeks Science Center, and Oconaluftee Visitor Center modeled separately. These rasters are Travel Time Cost Surface Models (TTCSM) created by NPS I&M staff, and models estimated travel time from starting locations to any point wihtin GRSM. Each model is for a different starting location: Park Headquarters (HQ), Twin Creeks Science Center (TWCR), and Oconaluftee Visitor Center (OVC). The models are created using the NPS TTCSM toolbox in ArcGIS, and raster values are in minutes traveled (rounded down to nearest minute). The resolution is 10M. The following assumptions are made by the modeling tool: 1. Travel starts at the given starting point, and then follows roads, trails, and off trail travel to reach any point. 2. No travel can occur on terrain with a slope of over 40 degrees. Areas on slopes over 40 degrees, or which cannot be reached without traversing said slopes, will return a NoData Value. 3. Travel values time out at 640 minutes (10 Hours, 40 minutes). After this, a NoData value is given. Generally, this only occurs in areas of signfiicantly steep slopes and dense understory vegetation. 4. Travel speed on roads is set as the legal speed limit. This model does allow travel on Administrative Roads, at a speed of 10 MPH. 5. Travel speed on trail is a function of slope, and of a user-defined speed reduction. For this model, GRSM public trails have no travel reduction, and un-maintained trails have a 50% travel reduction. 6. Off-trail travel speed is a function of slope, and a user-defined reduction of speed due to land cover. For the purpose of this model, areas with HIGH level of understory veg and/or significant wind damage are reduced 90%. Those with a medium level of understory vegetation reduced 66%, and those with light-to-no understory vegetation are reduced 50%. 7. The model allows for boat travel across Fonana Lake at a speed of 15 MPH, and access to administrative roads across the lake. Park streams do not effect the model, except that several user-defined high volume streams are set to a 90% time reduction (this eliminates the model from following large streams, where topography is often flatter). 8. Maximum walking speed is 3 mph, which can only occur on flat ground with no travel speed reductions. The model assumes no fatigue. Speed is reduced as slope increases and as various ground conditions are encountered. 9. Travel through non-park property is generally not allowed (except in a few instances of right-of-ways). Travel on non-park roads is allowed though, where they are included in model.

Marketing Mix Modeling for Travel Market Outlook

According to our latest research, the Global Marketing Mix Modeling for Travel market size was valued at $2.3 billion in 2024 and is projected to reach $7.6 billion by 2033, expanding at an impressive CAGR of 14.1% during the forecast period of 2025 to 2033. One of the primary factors driving this robust growth is the increasing digitalization of the travel industry, which has led to a surge in data-driven marketing strategies. As travel brands compete for consumer attention across multiple channels, the need for sophisticated marketing mix modeling solutions that can optimize media spend, channel allocation, and campaign effectiveness has never been greater. This trend is further amplified by the growing adoption of artificial intelligence and machine learning in marketing analytics, enabling travel companies to derive actionable insights from complex, multi-source data environments.

Regional Outlook

North America currently commands the largest share of the Marketing Mix Modeling for Travel market, accounting for approximately 38% of global revenue in 2024. The region's dominance is attributed to its mature travel sector, high penetration of advanced analytics technologies, and the presence of leading travel and hospitality brands that are early adopters of marketing optimization tools. Additionally, regulatory frameworks supporting data privacy and transparency have fostered trust and accelerated the implementation of marketing mix modeling solutions. The United States, in particular, stands out due to its strong ecosystem of technology vendors, consulting firms, and a culture of innovation in marketing science, which collectively drive the adoption of sophisticated analytics platforms across airlines, hotels, and online travel agencies.

Asia Pacific is emerging as the fastest-growing region in the Marketing Mix Modeling for Travel market, with a projected CAGR of 17.8% from 2025 to 2033. This rapid expansion is fueled by increasing investments in digital infrastructure, the proliferation of mobile-first consumers, and the exponential rise of online travel agencies in countries such as China, India, and Southeast Asia. The region's travel sector is undergoing a transformative shift as brands seek to personalize offerings and optimize marketing ROI in a highly competitive landscape. Governments and private players are investing heavily in smart tourism initiatives, further boosting demand for advanced analytics and marketing optimization solutions. As international travel rebounds post-pandemic, the need for real-time, data-driven decision-making is expected to accelerate marketing mix modeling adoption across the Asia Pacific region.

Emerging economies in Latin America, the Middle East, and Africa are also witnessing an uptick in the adoption of Marketing Mix Modeling for Travel, though growth is tempered by challenges such as limited access to high-quality data, fragmented travel ecosystems, and varying regulatory standards. In these markets, travel companies are increasingly recognizing the value of marketing analytics for targeting niche consumer segments and optimizing limited marketing budgets. However, adoption is often hindered by skills gaps, infrastructure constraints, and the need for localized solutions that account for cultural and linguistic diversity. Policy reforms aimed at boosting tourism and digital transformation are expected to gradually improve market penetration, positioning these regions for steady, albeit slower, growth over the forecast period.

Report Scope

This study analyzed regional travel patterns, network structures, and core areas using origin-destination (OD) data based on travel volume, to aid policies that address the concentration of resources in South Korea’s capital region. To identify the differences between passenger and freight travel, the functional regional structure of the network was analyzed using block modeling, while weighted centrality was examined to extract core cities from a polycentric urban perspective. Additionally, a multiple regression analysis was conducted to compare the factors influencing the core areas of passenger and freight flows. The findings are as follows: (1) Freight travel is more active between regions compared with passenger travel, suggesting that freight travel primarily relies on long-distance movement. (2) For passenger travel, geographically central cities emerged as core areas, whereas for freight travel, peripheral cities were identified as the major hubs. (3) Passenger travel was influenced by regional characteristics, industry, and infrastructure, whereas freight travel was primarily affected by regional characteristics, infrastructure, and land use patterns. Particularly, population density and industrial facilities significantly impacted both passenger and freight travel. Therefore, this study highlights the distinct characteristics of passenger and freight travel, offering insights to promote balanced development.

Marketing Mix Modeling for Travel Market Outlook

According to our latest research, the global Marketing Mix Modeling for Travel market size reached USD 1.42 billion in 2024, with a robust growth trajectory supported by evolving digital transformation and data-driven decision-making within the travel sector. The market is expected to expand at a CAGR of 12.7% from 2025 to 2033, projecting a value of USD 4.17 billion by 2033. This remarkable growth is being propelled by the increasing adoption of advanced analytics, real-time data integration, and the need for precise marketing ROI measurement in a highly competitive travel industry landscape.

One of the primary growth drivers for the Marketing Mix Modeling for Travel market is the exponential rise in digital marketing investments by travel companies. As consumer behavior continues to shift towards online channels, travel businesses are compelled to optimize their marketing strategies across multiple touchpoints. The ability of marketing mix modeling (MMM) to provide actionable insights into the effectiveness of various marketing channels, such as digital ads, social media, and offline campaigns, has made it indispensable for airlines, hotels, and online travel agencies. The growing complexity of customer journeys and the proliferation of data sources have further underscored the need for sophisticated modeling solutions that can handle large datasets and deliver granular insights, thereby driving market growth.

Another significant factor fueling the market is the increasing pressure on travel companies to maximize return on investment (ROI) in an environment marked by fluctuating demand and economic uncertainty. The travel sector, being highly sensitive to macroeconomic trends, seasonality, and global events, requires agile marketing strategies that can quickly adapt to changing market conditions. MMM enables travel businesses to allocate budgets more efficiently, identify underperforming campaigns, and forecast the impact of marketing activities on sales and bookings. The integration of artificial intelligence and machine learning algorithms into MMM platforms has further enhanced their predictive capabilities, allowing travel enterprises to stay ahead of competitors and respond proactively to market shifts.

The surge in personalized marketing and customer experience initiatives is also contributing to the adoption of marketing mix modeling in the travel industry. As travelers increasingly seek tailored experiences, travel brands are leveraging MMM to understand the interplay between personalization efforts and overall marketing performance. The ability to measure the incremental impact of targeted campaigns, loyalty programs, and dynamic pricing strategies is crucial for driving customer acquisition and retention. Moreover, regulatory changes and data privacy concerns have prompted travel companies to invest in secure and compliant MMM solutions that can deliver insights without compromising consumer trust. These trends collectively reinforce the market's upward trajectory.

Regionally, North America continues to dominate the Marketing Mix Modeling for Travel market, accounting for the largest revenue share in 2024. This leadership position is attributed to the high concentration of technologically advanced travel companies, early adoption of analytics platforms, and a mature digital marketing ecosystem. Europe follows closely, driven by the presence of global hotel chains and a rapidly evolving online travel agency landscape. Asia Pacific is emerging as the fastest-growing region, fueled by rising disposable incomes, expanding internet penetration, and a burgeoning travel and tourism sector. The Middle East & Africa and Latin America are also witnessing increased adoption, supported by government initiatives to boost tourism and digital transformation efforts among local travel businesses.

Component Analysis

The Marketing Mix Modeling for Travel market is segmented by component into software and services, each playing a

Urban SDK is a GIS data management platform and global provider of mobility, urban characteristics, and alt datasets. Urban SDK Traffic data provides traffic volume, average speed, average travel time and congestion for logistics, transportation planning, traffic monitoring, routing and urban planning. Traffic data is generated from cars, trucks and mobile devices for major road networks in US and Canada.

"With the old data I used, it took me 3-4 weeks to create a presentation. I will be able to do 3-4x the work with your Urban SDK traffic data."

Traffic Volume, Speed and Congestion Data Type Profile:

• Traffic volume in annual average daily and daily traffic volumes per roadway
• Average travel speed in 15 minute and hourly intervals per roadway
• Travel time in seconds in 15 minute intervals per roadway
• Commute travel time in minutes in annual interval estimates in geohash boundaries
• Congested roadway segments based on travel time reliability in monthly intervals per roadway
• Traffic data attributed spatially to state, county, road functional class, road name, road segment, segment length in km or miles as geojson

Industry Solutions include:

• Transportation Planning
• Traffic Monitoring
• Congestion Management and Trend Analysis
• Travel Demand Modeling
• Traffic Impact Analysis
• Parking Analysis
• Transit System Planning
• Route Planning
• Civil Engineering
• Site Selection

Use cases:

• Traffic monitoring, data analysis, and forecasting for transportation, transit, and urban planning.
• Improve dynamic routing with accurate travel time and congestion data
• Environmental and emissions analysis
• Travel demand and transportation modeling
• Location analysis and assessment for commercial site selection for retail or logistics related locations

This dataset describes the distribution (in number of tracers) of downstream travel distances calculated from field-measured PIT-tagged particles, two-dimensional hydrodynamic modeling and probabilistic modeling in the Ain River channel over the periods 2013-2014, 2013-2015 and 2013-2017.

1) Data Introduction • The Expedia Travel Dataset is a large travel data that contains information about users' clicks and bookings on Expedia.

2) Data Utilization (1) Expedia Travel Dataset has characteristics that: • This dataset includes information such as destinations, hotels, and the number of visitors, as well as details about the type of reservation. (2) Expedia Travel Dataset can be used to: • Development of travel recommendation system and reservation prediction model: User search patterns and accommodation selection data can be used to develop travel platform recommendation systems and consumer behavior prediction models, such as custom hotel recommendations, click and reservation predictions. • Analysis of tourism trends and consumer behavior: By analyzing various variables and actual selection data such as travel timing, region, type of accommodation, price range, and filter use, it can be used for research on the tourism industry, such as global tourism trends, changing consumer preferences, and establishing marketing strategies.

The datasets in this zip file are in support of Intelligent Transportation Systems Joint Program Office (ITS JPO) report FHWA-JPO-16-385, "Analysis, Modeling, and Simulation (AMS) Testbed Development and Evaluation to Support Dynamic Mobility Applications (DMA) and Active Transportation and Demand Management (ATDM) Programs — Evaluation Report for ATDM Program," and FHWA-JPO-16-389, "Analysis, Modeling, and Simulation (AMS) Testbed Development and Evaluation to Support Dynamic Mobility Applications (DMA) and Active Transportation and Demand Management (ATDM) Programs : Evaluation Report for the San Diego Testbed : Draft Report". The files in this zip file are specifically related to the San Diego Testbed. The compressed zip files total 3.17 GB in size. The files have been uploaded as-is; no further documentation was supplied by NTL. Direct download of data zip file: https://doi.org/10.21949/1500873 All located .docx files were converted to .pdf document files which are an open, archival format. These pdfs were then added to the zip file alongside the original .docx files. These files can be unzipped using any zip compression/decompression software. This zip file contains files in the following formats: .pdf document files which can be read using any pdf reader; .cvs text files which can be read using any text editor; .txt text files which can be read using any text editor; .docx document files which can be read in Microsoft Word and some other word processing programs; . xlsx spreadsheet files which can be read in Microsoft Excel and some other spreadsheet programs; .dat data files which may be text or multimedia; as well as GIS or mapping files in the following formats: .mxd, .dbf, .prj, .sbn, .shp., .shp.xml; which may be opened in ArcGIS or other GIS software. [software requirements] These files were last accessed in 2017.

Content

United Airlines yearly passenger data from 1995 to 2020 is included in this dataset. It contains data on the overall number of passengers transported, the frequency of flights, and operating patterns throughout the last 25 years. The information offers a thorough analysis of the airline's performance, emphasizing significant swings impacted by international events, market dynamics, and economic circumstances.

Context

The dataset is a useful tool for examning long term travel patterns in the aviation sector. It can be used by researchers, data analysts, and aviation experts to anticipate future travel demands, evaluate the effects of economic cycles, and examine passenger growth trends. In studies on air transport, it also facilitates predictive modeling and exploratory data analysis (EDA).

Acknowledgement

As a valuable resource for making United Airlines passenger data publicly available for analysis and research

The data contains a synthetic replica of over 10 million Swedish individuals (i.e., agents), their household characteristics, and activity-travel plans. The datasets are stored in a relational database format in Person, Household, and Activity-travel tables. The Person table contains the synthetic agents' socio-demographic attributes, such as age, gender, civil status, residential zone, personal income, car ownership, employment, etc. The Household table stores agents' household attributes such as household type, size, number of children, and number of cars. The Activity-travel table contains the daily activity schedules of agents, i.e., where and when they do certain activities (work, home, school, and other) and how they travel between them (walk, bike, car, and public transport).

This zip file contains POSTDATA.ATT (.ATT); Print to File (.PRN); Portable Document Format (.PDF); and document (.DOCX) files of data to support FHWA-JPO-16-385, Analysis, modeling, and simulation (AMS) testbed development and evaluation to support dynamic mobility applications (DMA) and active transportation and demand management (ATDM) programs — evaluation report for ATDM program. Zip size is 168 MB. Files were accessed in 2017. Data will be preserved as is.

DRAKO is a Mobile Location Data provider with a programmatic trading desk specializing in geolocation analytics and programmatic advertising. Our Consumer Travel History Data has helped cities, counties, and states better understand who their visitors are so that they can effectively develop and deliver advertising campaigns. We’re in a unique position to deliver enriched insight beyond traditional surveying or other data sources because of our rich dataset, proprietary modelling capabilities, and analytical capabilities.

MAIDs (Mobile Advertising IDs) are unique device identifiers associated with consenting mobile devices that can be utilized for geolocation based analyses and audiences. Drako uses MAIDs to fuel our Consumer Travel History Data utilizing our Home Location Model. The Home Location of a MAID is determined based on where that MAID is seen most frequently between the hours of 11pm and 6am (local time). Using this we are able to determine the Home Location of a user which in turn allows us to identify when and where they are travelling.

Beyond identifying that users are tourists, we can also classify them into different bins by their frequency / dwell time over their estimated number of visits. Using our data and frequency, we can identify: overnight visitors, weekend visits, short-term stays, long-term stays, or frequent holiday visitors !

Beyond Consumer Travel History Data in your defined geography alone, we are also able to provide: - Home location - Find out where your audience is coming from using our home location technology - Movement - Quantify how far users have travelled between locations. - Demographics - Discover neighborhood level characteristics such as income, ethnicity, and more - Brand index - Learn which major brands and retailers your audience is visiting the most. - Visitation index - See which destinations your visitors are visiting the most - Addressable audience - Customize your audiences for your campaigns using our analytic insights

Moreover, if you’re looking to activate your Consumer Travel History Data for advertising, we’re always able to further refine or filter your desired audience with our other Audience Data, such as: Brand visits, Geodemographics, Ticketed Event visits, Purchase Intent (in Canada), Purchase History (in USA), and more !

Data Compliance: All of our Consumer Travel History Data is fully CCPA compliant and 100% sourced from SDKs (Software Development Kits), the most reliable and consistent mobile data stream with end user consent available with only a 4-5 day delay. This means that our location and device ID data comes from partnerships with over 1,500+ mobile apps. This data comes with an associated location which is how we are able to segment using geofences.

Data Quality: In addition to partnering with trusted SDKs, DRAKO has additional screening methods to ensure that our mobile location data is consistent and reliable. This includes data harmonization and quality scoring from all of our partners in order to disregard MAIDs with a low quality score.

This Polygon layer is based on a map showing the draft number of jobs in 2023 by transportation analysis zone (TAZ) in the state's rural areas, and it is meant to help collect comments from local governments on the displayed data. This layer is part of a web map app that the UDOT Planning Analytics team will review the comments, and make adjustments to finalize the underlying data. The final 2023 number of jobs dataset will be used to support the 2027-2055 Long Range Planning process.For GIS questions, please contact Muna Shah, GIS Planning Manager, at mshah@utah.gov. For data or process questions, please contact Natalia Brown, Travel Demand Model Program Manager, at nataliabrown@utah.gov.

This zip file contains files of data to support FHWA-JPO-16-370, Analysis, Modeling, and Simulation (AMS) Testbed Development and Evaluation to Support Dynamic Mobility Applications (DMA) and Active Transportation and Demand Management (ATDM) Programs - San Mateo Testbed Analysis Plan : Final Report. Zip size is 1.5 GB. The files have been uploaded as-is; no further documentation was supplied by NTL. All located .docx files were copied to .pdf document files which are an archival format. These .pdfs were then added to the zip file alongside the original .docx files. The attached zip files can be unzipped using any zip compression/decompression software. These zip file contains files in the following formats: .pdf document files which can be read using any pdf reader; .docx document files which may be opened with Microsoft Word or some other open source document editors; .xlsx spreadsheet files which may be opened with Microsoft Excel or some other open source spreadsheet editors; .syn files are a proprietary file format for signal timing plans which are provided in the Synchro Model given as “El Camino Real Synchro.syn” and can be opened using Trafficware Synchro, which may require users to purchase a license or software (for more information go to http://www.trafficware.com/); .csv data files, an open format, which may be opened with any text editor or in many spreadsheet applications; .db generic database files, often associated with thumbnail images in the Windows operating environment; .rbc files, which are scripts written in Rembo-C, which can be opened in a text editor, but require a server with Rembo installed to run the scripts; .vap audio files which will require special audio editing software to manipulate; .dll dynamically linked files for Windows program operations; .layx, a file type on which we could not locate reliable information; and .inpx files, a file type on which we could not locate reliable information [software requirements]. These files were last accessed in 2017. Files were accessed in 2017. Data will be preserved as is.

To reduce inaccuracies due to insufficient spatial resolution of models, it has been suggested to use smaller raster cells instead of larger zones. Increasing the number of zones, however, increases the size of a matrix to store travel times, called skim tables in transport modeling. Those become difficult to create, to store and to read, while most of the origin-destination pairs are calculated and stored but never used. At the same time, such approaches do not solve inaccuracies due to lack of temporal resolution. This paper analyzes the use of personalized travel times at the finest spatial resolution possible (at x/y coordinates) and a detailed temporal resolution for synthetic agents. The approach is tested in the context of an existing integrated land use/transport model (ILUT) where travel times affect, among others, household relocation decisions. In this paper, person-level individual travel times are compared to traditional skim-based travel times to identify the extent of errors caused by spatial and temporal aggregation and how they affect relocation decisions in the model. It was shown that skim-based travel times fail to capture the spatial and temporal variations of travel times available at a microscopic scale of an agent-based ILUT model. Skims may provide acceptable averages for car travel times if a dense network and small zones are used. Transit travel times, however, suffer from temporal and spatial aggregation of skims. When analyzing travel-time-dependent relocation decisions in the land use model, transit captive households tend to react more sensitively to the transit level of service when individual travel times are used. The findings add to the existing literature a quantification of spatial biases in ILUT models and present a novel approach to overcome them. The presented methodology eliminates the impact of the chosen zone system on model results, and thereby, avoids biases caused by the modifiable spatial unit problem.

Travel model data for years 2032 and 2050 for rural portions of Utah. This information is used to inform the 2023 Long Range Plan. Data is from LRP 2023 Travel Models and is not refreshed. This feature is intended to support the 2023 Long Range Plan planning process. For more information please contact Andrea Moser at amoser@bio-west.com

Travel regions are not necessarily defined by political or administrative boundaries. For example, in the Schengen region of Europe, tourists can travel freely across borders irrespective of national borders. Identifying transboundary travel regions is an interesting problem which we aim to solve using mobility analysis of Twitter users. Our proposed solution comprises collecting geotagged tweets, combining them into trajectories and, thus, mining thousands of trips undertaken by twitter users. After aggregating these trips into a mobility graph, we apply a community detection algorithm to find coherent regions throughout the world. The discovered regions provide insights into international travel and can reveal both domestic and transnational travel regions.

Dataset Description for Tour Recommendation Model

Context and Methodology:

• Research Domain/Project:
  This dataset is part of the Tour Recommendation System project, which focuses on predicting user preferences and ratings for various tourist places and events. It belongs to the field of Machine Learning, specifically applied to Recommender Systems and Predictive Analytics.

• Purpose:
  The dataset serves as the training and evaluation data for a Decision Tree Regressor model, which predicts ratings (from 1-5) for different tourist destinations based on user preferences. The model can be used to recommend places or events to users based on their predicted ratings.

• Creation Methodology:
  The dataset was originally collected from a tourism platform where users rated various tourist places and events. The data was preprocessed to remove missing or invalid entries (such as #NAME? in rating columns). It was then split into subsets for training, validation, and testing the model.

Technical Details:

• Structure of the Dataset:
  The dataset is stored as a CSV file (user_ratings_dataset.csv) and contains the following columns:

  • place_or_event_id: Unique identifier for each tourist place or event.

  • rating: Rating given by the user, ranging from 1 to 5.

  The data is split into three subsets:

  • Training Set: 80% of the dataset used to train the model.

  • Validation Set: A small portion used for hyperparameter tuning.

  • Test Set: 20% used to evaluate model performance.

• Folder and File Naming Conventions:
  The dataset files are stored in the following structure:

  • user_ratings_dataset.csv: The original dataset file containing user ratings.

  • tour_recommendation_model.pkl: The saved model after training.

  • actual_vs_predicted_chart.png: A chart comparing actual and predicted ratings.

• Software Requirements:
  To open and work with this dataset, the following software and libraries are required:

  • Python 3.x

  • Pandas for data manipulation

  • Scikit-learn for training and evaluating machine learning models

  • Matplotlib for chart generation

  • Joblib for saving and loading the trained model

  The dataset can be opened and processed using any Python environment that supports these libraries.

• Additional Resources:

  • The model training code, README file, and performance chart are available in the project repository.

  • For detailed explanation and code, please refer to the GitHub repository (or any other relevant link for the code).

Further Details:

• Dataset Reusability:
  The dataset is structured for easy use in training machine learning models for recommendation systems. Researchers and practitioners can utilize it to:

  • Train other types of models (e.g., regression, classification).

  • Experiment with different features or add more metadata to enrich the dataset.

• Data Integrity:
  The dataset has been cleaned and preprocessed to remove invalid values (such as #NAME? or missing ratings). However, users should ensure they understand the structure and the preprocessing steps taken before reusing it.

• Licensing:
  The dataset is provided under the CC BY 4.0 license, which allows free usage, distribution, and modification, provided that proper attribution is given.