sparsity

The task is to build a recommender system for an educational platform. Namely, you need to train a model that will recommend 3 courses (course_id) to each user (user name is encoded via user_id) from those that they have not yet taken. The model should be able to work with both old users and new users who have not yet purchased any courses.

Important: it is necessary to recommend courses to the user only from those that they have not yet taken.

Data

To build the model, you will have access to various data about the courses taken by users, as well as a test set of user_id, for which you need to make predictions. train.csv - user-course table with information about the courses taken by users

user_id - unique user identifier item_id - unique course identifier

The test data is presented in the submission.csv file This file contains the test user_ids for which predictions need to be made. As well as the format of the test predictions - predicted course_ids for a specific user with user_id. The order of the predictions does not matter, it is important that the correct courses are among your three predictions. For example, for a user with user_id 42, the correct courses are course_id 4, 8, 15. Any permutation of (4, 15, 8), (8, 4, 15), etc. will be counted as correct

Students data with all attributes for course recommendation system

Course recommendation aims at finding proper and attractive courses from massive candidates for students based on their needs, and it plays a significant role in the curricula-variable system. However, nearly all students nowadays need help selecting appropriate courses from abundant ones. The emergence and application of personalized course recommendations can release students from that cognitive overload problem. However, it still needs to mature and improve its scalability, sparsity, and cold start problems resulting in poor quality recommendations. Therefore, this paper proposes a novel personalized course recommendation system based on deep factorization machine (DeepFM), namely Deep PersOnalized couRse RecommendatIon System (DORIS), which selects the most appropriate courses for students according to their basic information, interests and the details of all courses. The experimental results illustrate that our proposed method outperforms other approaches.

These datasets include ratings as well as social (or trust) relationships between users. Data are from LibraryThing (a book review website) and epinions (general consumer reviews).

Metadata includes

• reviews

• price paid (epinions)

• helpfulness votes (librarything)

• flags (librarything)

Dataset

This dataset was created by huuphat

Contents

Course recommendation aims at finding proper and attractive courses from massive candidates for students based on their needs, and it plays a significant role in the curricula-variable system. However, nearly all students nowadays need help selecting appropriate courses from abundant ones. The emergence and application of personalized course recommendations can release students from that cognitive overload problem. However, it still needs to mature and improve its scalability, sparsity, and cold start problems resulting in poor quality recommendations. Therefore, this paper proposes a novel personalized course recommendation system based on deep factorization machine (DeepFM), namely Deep PersOnalized couRse RecommendatIon System (DORIS), which selects the most appropriate courses for students according to their basic information, interests and the details of all courses. The experimental results illustrate that our proposed method outperforms other approaches.

The current worldwide pandemic has significantly increased the need for online learning platforms, hence presenting difficulty in choosing appropriate course materials from the vast online educational resources due to user knowledge frameworks variations. This paper presents a novel course recommendation system called the Deep Learning-based Course Recommendation System (DLCRS). The DLCRS combines a hybrid Sequential GRU+adam optimizer with collaborative filtering techniques to offer accurate and learner-centric course suggestions. The proposed approach integrates modules for learner feature extraction and course feature extraction that is performed using (Embeddings from Language Models) ELMO word embedding technique in order to gain a thorough understanding of learner and course profiles and feedback. In order to evaluate the efficacy of the proposed DLCRS, several extensive experiments were carried out utilizing authentic datasets sourced from a reputable public organization. The results indicate a notable area under the receiver operating characteristic curve (AUC) score of 89.62%, which exceeds the performance of similar advanced course recommendation systems. The experimental findings support the viability of the DLCRS, as seen by a significant hit ratio of 0.88, indicating high accuracy in its suggestions.

Using a variation of a correspondence audit study, we show that, even after controlling for how prepared a candidate seems, White males are more likely to be recommended for AP Calculus. In this setting, name-blind review does not improve the likelihood of recommendation for any race/gender group and can actually be harmful rather than simply bias-reducing. This is the data and code for replication of the results in the paper.

In this paper

These datasets contain reviews from the Steam video game platform, and information about which games were bundled together.

Metadata includes

• reviews

• purchases, plays, recommends (likes)

• product bundles

• pricing information

Basic Statistics:

• Reviews: 7,793,069

• Users: 2,567,538

• Items: 15,474

• Bundles: 615

These datasets contain peer-to-peer trades from various recommendation platforms.

Metadata includes

• peer-to-peer trades

• have and want lists

• image data (tradesy)

The intial purpose of this dataset extraction was to extract the relevant skills that can be obtained from each course from Coursera. The skills then can be used for further analytical use. Feel free to use the dataset at your own use cases.

About this repository

This dataset contains information queried from 22 students inside a Moodle based learning management system during the winter term 2023/24 at a German university.

Abstract

With the use of learning management systems students benefit from being recommended suitable learning elements based on their individual needs. In doing so, recommendation algorithms are applied which first query the student’s learning style. To improve the recommendation of learning elements a continuous analysis of the individual’s learning style is required. A frequent questionnaire assessment would however be too time consuming. Instead, in a prior study an algorithm has been designed to identify changes in learning styles from the student’s selection of learning elements. In this paper, we investigate the functionality of that algorithm by applying it on real student data. In particular, we test if the algorithm correctly indicates changes in learning styles. The utilised data is collected in our learning management system. To be precise, the data is obtained from 22 students enrolled in a software engineering course during the winter term of 2023/24. The data comprises two types of information for each student: 1) learning style collected at the start and end of the term, and 2) the user’s actual selection of learning elements inside the learning management system.
The uniqueness of this study lies in the data and the evaluation strategy based on it. Having the learning style at the end of the semester period as ground truth allows us to test if the algorithm operates correctly with actual user data from our learning management system. The results validate the behaviour of our algorithm, yet they strongly suggest the need for an adaptation. Further research is required on how to parameterise the underlying models.

Data Explanation

This dataset contains

• ILS learning styles queried at the start and end of the semester period (winter term 2023/24)
• sequences of learning elements chosen inside a Moodle based learning management system.

The learning elements are chosen according to the learning element defined by Staufer et al. in "LEARNING ELEMENTS IN ONLINE LEARNING MANAGEMENT SYSTEMS" (doi:https://doi.org/10.21125/iceri.2023.0815">10.21125/iceri.2023.0815)

Acknowledgments

The present paper is supported by the ‘German Federal Ministry of Education and Research’ (BMBF) through the granting of the funding project HASKI (FKZ: 16DHBKI035)

Contact Information

If you have any questions feel free to reach out to the owners of this repository by mail: flemming.bugert(a)oth-regensburg.de

These datasets contain reviews from the Goodreads book review website, and a variety of attributes describing the items. Critically, these datasets have multiple levels of user interaction, raging from adding to a shelf, rating, and reading.

Metadata includes

• reviews

• add-to-shelf, read, review actions

• book attributes: title, isbn

• graph of similar books

Basic Statistics:

• Items: 1,561,465

• Users: 808,749

• Interactions: 225,394,930

Online Course Booking System Market Outlook

The global market size for Online Course Booking Systems was valued at USD 2.5 billion in 2023 and is projected to reach USD 7.8 billion by 2032, growing at a compound annual growth rate (CAGR) of 13.4% over the forecast period. This dynamic growth is driven by an increased demand for flexible and accessible education solutions, the rise of e-learning platforms, and technological advancements in cloud computing and data analytics.

One of the key growth factors for this market is the escalating demand for remote learning solutions. The COVID-19 pandemic has accelerated the adoption of online learning platforms as educational institutions and corporate entities pivot to digital solutions to ensure continuity in education and training. As a result, many providers are investing heavily in developing robust, user-friendly online course booking systems that can handle a large volume of users while providing a seamless experience. Furthermore, the versatility and convenience offered by these systems are encouraging more institutions to adopt them, enhancing market growth.

Another significant driver for this market is the increasing penetration of smartphones and high-speed internet, which makes online learning more accessible. As more people gain access to these digital tools, the demand for online courses—and by extension, online course booking systems—continues to rise. Additionally, the growing preference for upskilling and reskilling among professionals to stay competitive in the job market is propelling the demand for professional and vocational courses, which in turn fuels the demand for efficient booking systems.

Technological advancements in artificial intelligence (AI) and machine learning (ML) are also playing a crucial role in shaping the market. AI-powered course recommendation engines, predictive analytics for student performance, and personalized learning paths are some of the innovations that are enhancing the efficacy of online course booking systems. These technologies not only improve the user experience but also provide valuable insights to course providers, enabling them to optimize their offerings and marketing strategies.

From a regional perspective, North America holds a significant share of the online course booking system market, driven by the presence of major educational institutions and corporate entities that are early adopters of advanced technologies. The region is expected to maintain its dominance due to ongoing investments in educational technology and the presence of key market players. Asia Pacific is anticipated to witness the highest CAGR during the forecast period, driven by the increasing focus on digital education and the growing number of internet users in countries like China, India, and Japan.

The integration of Class Registration Software into online course booking systems is becoming increasingly vital for educational institutions and corporate training programs. This software streamlines the entire registration process, allowing users to easily enroll in courses, manage schedules, and make payments. By automating these tasks, institutions can reduce administrative burdens and enhance the user experience. The ability to handle large volumes of registrations efficiently is particularly beneficial during peak enrollment periods, ensuring that learners have a smooth and hassle-free experience. Furthermore, Class Registration Software often includes features such as waitlist management and automated notifications, which help institutions maintain high levels of engagement and satisfaction among their users.

Component Analysis

The online course booking system market is segmented by components into software and services. The software segment comprises platforms and applications that facilitate course booking, management, and delivery. This segment is likely to dominate the market due to the growing demand for intuitive and comprehensive software solutions that can handle a myriad of functionalities such as scheduling, payment processing, and user management. The increasing adoption of cloud-based solutions further bolsters the growth of this segment, as it offers scalability, flexibility, and cost-efficiency.

The services segment includes consulting, implementation, and maintenance services that support the deployment and operation of online course booking systems. As educational institutions and corporate entities

This dataset contains images (scenes) containing fashion products, which are labeled with bounding boxes and links to the corresponding products.

Metadata includes

• product IDs

• bounding boxes

Basic Statistics:

• Scenes: 47,739

• Products: 38,111

• Scene-Product Pairs: 93,274

We introduce PDMX: a Public Domain MusicXML dataset for symbolic music processing, including over 250k musical scores in MusicXML format. PDMX is the largest publicly available, copyright-free MusicXML dataset in existence. PDMX includes genre, tag, description, and popularity metadata for every file.

MAE score.

The CDEI has been tasked with researching the ways in which algorithmically driven recommendation systems have impacted music consumption, including how creators are being affected (see Recommendation 18 in the government’s response to the economics of music streaming Committee’s Second Report). The CDEI will be carrying out a survey to take the views of creators into consideration as part of our research, as well as begin to understand if and how algorithmically driven recommendation systems affect different categories of creators, creators across different genres, and whether there are any apparent differences in their effect by region, age, gender identity, or ethnic group. This privacy notice explains who the CDEI are, the personal data the CDEI collects, how the CDEI uses it, who the CDEI shares it with, and what your legal rights are.