A Multi-Stage Framework for Chess Puzzle Difficulty Prediction

Accurately estimating the difficulty of the chess puzzle is important for adaptive training systems, personalized recommendations, and large-scale content curation.Unlike engine evaluations optimized for perfect play, this task involves modeling human-perceived solving difficulty, typically expressed by Glicko-2 ratings.We present a multi-stage framework developed for the FedCSIS 2025 Challenge.The method trains four rating-banded neural regression models in different Elo ranges to capture localized difficulty patterns and reduce bias from unbalanced data.Their predictions are combined with statistical attributes, including success probabilities, failure distributions, and solution length, through a feature-based regression stage to improve cross-range generalization.A final calibration step adjusts the output to statistically plausible rating levels, mitigating systematic prediction biases without adding computational complexity.An additional mask selection procedure was explored as part of the competition extension to identify 10% of the puzzles that are most likely to benefit from the refined evaluation.The proposed solution ranked 5 th on the public leaderboard and 6 th in the final standings.These results demonstrate that a lightweight and interpretable regression pipeline can achieve competitive precision in modeling human-perceived chess puzzle difficulty.