{"total":28,"rows":[{"id":"2104.00629","title":"Regularized target encoding outperforms traditional methods in supervised machine learning with high cardinality features","created":"2021-04-01","cited_by_count":21,"area":null},{"id":"2201.11358","title":"Fairness Implications of Encoding Protected Categorical Attributes","created":"2022-01-27","cited_by_count":7,"area":null},{"id":"2301.12710","title":"Machine Learning with High-Cardinality Categorical Features in Actuarial Applications","created":"2023-01-30","cited_by_count":7,"area":null},{"id":"2307.09191","title":"A benchmark of categorical encoders for binary classification","created":"2023-07-17","cited_by_count":6,"area":null},{"id":"2206.01409","title":"Hybrid Parameter Search and Dynamic Model Selection for Mixed-Variable Bayesian Optimization","created":"2022-06-03","cited_by_count":4,"area":null},{"id":"2607.00477","title":"Interpretable vs Learned Encoders for High-Cardinality Fraud Detection","created":"2026-07-01","cited_by_count":3,"area":null},{"id":"2311.16984","title":"FedECA: Federated External Control Arms for Causal Inference with Time-To-Event Data in Distributed Settings","created":"2023-11-28","cited_by_count":2,"area":null},{"id":"2401.09682","title":"Comparative Study on the Performance of Categorical Variable Encoders in Classification and Regression Tasks","created":"2024-01-18","cited_by_count":2,"area":null},{"id":"2110.10059","title":"On Clustering Categories of Categorical Predictors in Generalized Linear Models","created":"2021-10-19","cited_by_count":1,"area":null},{"id":"2111.11956","title":"ptype-cat: Inferring the Type and Values of Categorical Variables","created":"2021-11-23","cited_by_count":1,"area":null},{"id":"2208.06262","title":"Identifying Substitute and Complementary Products for Assortment Optimization with Cleora Embeddings","created":"2022-08-10","cited_by_count":1,"area":null},{"id":"2211.02943","title":"Predicting Treatment Adherence of Tuberculosis Patients at Scale","created":"2022-11-05","cited_by_count":1,"area":null},{"id":"2403.19405","title":"Tabular Learning: Encoding for Entity and Context Embeddings","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2406.19136","title":"YZS-model: A Predictive Model for Organic Drug Solubility Based on Graph Convolutional Networks and Transformer-Attention","created":"2024-06-27","cited_by_count":1,"area":null},{"id":"2512.07865","title":"Using Text-Based Life Trajectories from Swedish Register Data to Predict Residential Mobility with Pretrained Transformers","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2602.21717","title":"C$^{2}$TC: A Training-Free Framework for Efficient Tabular Data Condensation","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2104.08044","title":"Holmes: An Efficient and Lightweight Semantic Based Anomalous Email Detector","created":"2021-04-16","cited_by_count":0,"area":null},{"id":"2111.01868","title":"From Strings to Data Science: a Practical Framework for Automated String Handling","created":"2021-11-02","cited_by_count":0,"area":null},{"id":"2206.02206","title":"Performance Comparison of Simple Transformer and Res-CNN-BiLSTM for Cyberbullying Classification","created":"2022-06-05","cited_by_count":0,"area":null},{"id":"2212.00892","title":"Progressive Feature Upgrade in Semi-supervised Learning on Tabular Domain","created":"2022-12-01","cited_by_count":0,"area":null},{"id":"2402.08109","title":"From Data to Decisions: The Transformational Power of Machine Learning in Business Recommendations","created":"2024-02-12","cited_by_count":0,"area":null},{"id":"2407.11286","title":"CLAMS: A System for Zero-Shot Model Selection for Clustering","created":"2024-07-15","cited_by_count":0,"area":null},{"id":"2508.12560","title":"Data-driven Trust Bootstrapping for Mobile Edge Computing-based Industrial IoT Services","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2602.00412","title":"Robustness of AutoML on Dirty Categorical Data","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.03967","title":"Non-linear PCA via Evolution Strategies: a Novel Objective Function","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2606.30336","title":"FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.08281","title":"Enhancing the KidSat Model: Integrating Geographical Encoding and Data Quality Assessment for Childhood Poverty Prediction","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.25751","title":"An Embarrassingly Simple Rule-based Visiting Circulation Approach to Trip Destination Prediction","created":"2026-07-28","cited_by_count":0,"area":null}],"next_cursor":null}