mlsanityData to 7 Oct 2026

Riiid! Answer Correctness Prediction Kaggle Challenge: 4th Place Solution Summary

arXiv 2102.04250 ↗First posted 3 Feb 2021cs.CY cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

This paper presents my solution to the challenge "Riiid! Answer Correctness Prediction" on Kaggle hosted by Riiid Labs (2020), which scores 0.817 (AUC) and ranks 4th on the final private leaderboard. It is a single transformer-based model heavily inspired from previous works such as SAKT, SAINT and SAINT+. Novel ingredients that I believed to have made a difference are the time-aware attention mechanism, the concatenation of the embeddings of the input sequences and the embedding of continuous features.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 6 of its 9 references that are in the map. First posted on arXiv 3 Feb 2021.

Builds on

6 of 9 references.

References · 6

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Layer Normalizationcited by 5,579
  3. 2019A Self-Attentive model for Knowledge Tracingcited by 169
  4. 2019EdNet: A Large-Scale Hierarchical Dataset in Educationcited by 106
  5. 2020Towards an Appropriate Query, Key, and Value Computation for Knowledge Tracingcited by 79
  6. 2020SAINT+: Integrating Temporal Features for EdNet Correctness Predictioncited by 57

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 1.

4 papers.

  1. 2024Time Series Analysis for Education: Methods, Applications, and Future Directionscited by 5
  2. 2023Multi-granulariy Time-based Transformer for Knowledge Tracingcited by 1
  3. 2022Incremental Knowledge Tracing from Multiple Schoolscited by 0
  4. 2023Improved Sales Forecasting using Trend and Seasonality Decomposition with LightGBMcited by 0