# Chess Rating Estimation from Moves and Clock Times Using a CNN-LSTM

arXiv: https://arxiv.org/abs/2409.11506 · HTML: https://mlsanity.com/paper/2409.11506/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 31 references that are in the map.
- First posted on arXiv 17 Sep 2024.

## Builds on (most cited first, 5 of 5)

- [Aligning Superhuman AI with Human Behavior: Chess as a Model System](https://mlsanity.com/paper/2006.01855/) (2020)
- [Amortized Planning with Large-Scale Transformers: A Case Study on Chess](https://mlsanity.com/paper/2402.04494/) (2024)
- [Learning Models of Individual Behavior in Chess](https://mlsanity.com/paper/2008.10086/) (2020)
- [QuickSkill: Novice Skill Estimation in Online Multiplayer Games](https://mlsanity.com/paper/2208.07704/) (2022)
- [Predicting User Perception of Move Brilliance in Chess](https://mlsanity.com/paper/2406.11895/) (2024)

## Built on by (most cited first, 4 of 4)

- [Predicting Chess Puzzle Difficulty with Transformers](https://mlsanity.com/paper/2410.11078/) (2024)
- [Policies of Multiple Skill Levels for Better Strength Estimation in Games](https://mlsanity.com/paper/2505.00279/) (2025)
- [ChessMimic: Per-Rating Transformer Models for Human Move, Clock, and Outcome Prediction in Online Blitz Chess](https://mlsanity.com/paper/2606.04473/) (2026)
- [Accelerating Skill Assessment in Chess: A Drift-Diffusion-Enhanced Elo Rating System](https://mlsanity.com/paper/2606.26267/) (2026)

## Abstract (arXiv)

Current chess rating systems update ratings incrementally and may not always accurately reflect a player's true strength at all times, especially for rapidly improving players or very rusty players. To overcome this, we explore a method to estimate player ratings directly from game moves and clock times. We compiled a benchmark dataset from Lichess with over one million games, encompassing various time controls and including move sequences and clock times. Our model architecture comprises a CNN to learn positional features, which are then integrated with clock-time data into a Bidirectional LSTM, predicting player ratings after each move. The model achieved an MAE of 182 rating points on the test data. Additionally, we applied our model to the 2024 IEEE Big Data Cup Chess Puzzle Difficulty Competition dataset, predicted puzzle ratings and achieved competitive results. This model is the first to use no hand-crafted features to estimate chess ratings and also the first to output a rating prediction after each move. Our method highlights the potential of using move-based rating estimation for enhancing rating systems and potentially other applications such as cheating detection.