Loading...
Loading...
Student performance, MOOC logs, knowledge tracing, standardized tests, learning analytics
13,411 datasets
Total pupil enrollment figures for primary education are reported by national governments. The Global Partnership for Education aggregates these country-specific definitions and methods. The temporal and geographic coverage of this collection is not specified.
Pupils entering primary school for the first time, excluding repeaters, are counted by national authorities. Country-specific definitions, methods, and targets are determined by the countries themselves. The Global Partnership for Education provides this data.
Student Performance Dataset is a dataset published on Kaggle. Its title suggests it contains information related to student academic outcomes. The specific source, size, and collection method are not detailed in the available metadata.
Brain tumor MRI image for Federated Learning is a collection of medical images hosted on Kaggle. The dataset likely contains MRI scans intended for use in federated learning scenarios. Specific details regarding the number of images, collection methodology, and source institution are not provided in the available metadata.
This dataset by Tarun Jain analyzes the relationship between official language policies and educational outcomes across Indian districts from the colonial era through the 1956 reorganization. It tracks literacy and college graduation rates to measure the impact of linguistic mismatches between the population and the medium of instruction. The data supports findings that mismatched districts experienced significantly lower educational achievement until political reorganization occurred.
Assessment data for Vermont schools, likely containing standardized test scores and performance indicators. The dataset includes columns such as IndicatorLabel, SchoolValue, SupervisoryUnionValue, SchoolYear, OrgName, AssessGroup, StateValue, SchoolIdentifier, TestName, and AssessLabel. It is published on the data.vermont.gov platform via Socrata and was last updated on 2026-02-18.
A dataset for modeling student performance. It likely contains records of student exam scores paired with study hours, intended for simple linear regression analysis. The dataset is hosted on Kaggle, but details on its origin, size, and collection period are unspecified.
Kaggle hosts a dataset for predicting student performance using multiple linear regression. The dataset's specific size, origin, and temporal details are not provided in the available metadata. Its primary purpose is to serve as a resource for building and testing regression models in an educational context.
Kaggle hosts this dataset concerning learner metrics and progress in music education. The data likely contains measurements for assessing student performance, potentially intended for AI-driven evaluation. The specific source, size, and collection details are not provided in the available metadata.
Bernkastel-Kues is a town in Germany. This dataset likely contains the geospatial location of a youth hostel situated on the Peter-Kremer-Weg school centre property. The data is provided by the Bundesamt für Kartographie und Geodäsie and was last updated on 2026-02-24.
Bundesamt für Kartographie und Geodäsie provides geospatial development plans for the Alte Weinbauschule (Old Wine School) district in Bernkastel-Kues, Germany. The data is served via a Web Map Service (WMS) format. It was last updated on 2026-02-24.
Oceanographic bottle measurements from the North Atlantic Ocean, including temperature, salinity, and oxygen data. The data was collected for the Baltimore Harbor Study under a contract between Johns Hopkins University and the Maryland Department of Research and Education. Measurements were taken from July 1958 to December 1960.
530,601 SwissProt proteins with substructure annotations from DSSP and InterPro release 103.0, stored as sharded JSONL files. The dataset, authored by rcalef, is intended for training and evaluating substructure-aware protein representation learning models. It was last updated on Hugging Face on February 24,我们发现了一个错误。
A collection of student reviews about Russian universities, authored by Andrey Zavodov and shared under a CC-BY-4.0 license. The dataset is hosted on OpenML and is described as a big dataset, though its specific size and update history are not provided. It is intended for tasks involving textual feedback in Russian.
Data from the 2014 Kaggle Higgs Boson Machine Learning Challenge, originally sourced from CERN. The dataset was used for a public competition to develop algorithms for distinguishing Higgs boson particle decay signals from background noise. Documentation is available from the challenge website and CERN's open data portal.
A binary classification dataset for predicting supplier risk. The dataset is hosted on Kaggle and is tagged for business operations and supply chain applications. The author, organization, and specific data collection details are not provided.
A SOAP web service provides geocoding and address verification operations for locations within Washington, D.C. The service, maintained by the District of Columbia government, supports code-based querying interfaces for developers.
A report reviewing education reform efforts in Pakistan and U.S. assistance, including a discussion of current policy. The report was authored by K. A. Kronstadt and published on the paperswithcode platform. The primary education system in Pakistan is described as ranking among the world's least effective, a matter identified as relevant to U.S. interests in South Asia.
A review paper critically appraising the measurement of social class and socioeconomic status in higher education research. The work argues for including subjective self-definitions alongside traditional objective measures like parental income and occupation. The author is Mark Rubin, sourced from the paperswithcode platform.
The WeightIt package generates balancing weights for causal effect estimation in observational studies. It supports binary, multi-category, or continuous point or longitudinal treatments by extending the functionality of several R packages and providing in-house estimation methods. Methods include parametric modeling, optimization, and machine learning, with tools for weight assessment and weighted regression via M-estimation or bootstrapping.