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

TL;DR

This paper introduces a novel CNN-LSTM model that estimates chess player ratings directly from move sequences and clock times, achieving accurate, move-by-move rating predictions without hand-crafted features.

Contribution

The study presents the first model to predict chess ratings after each move using only move sequences and clock data, outperforming traditional incremental rating systems.

Findings

Achieved an MAE of 182 rating points on test data.

Successfully predicted puzzle ratings in a competitive dataset.

First to use no hand-crafted features for move-based rating estimation.

Abstract

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.