Comparative Analysis of Crossword Puzzle Scoring Prediction Models Based on BP Neural Network

BP neural network model is used to predict the probability of a word appearing in 2023 “World” crossword game. By analyzing the score data reported by players on Twitter, we use BP neural network model to build the model and check the accuracy of the model. The results showed that the predicted ratio of 7 cases was 0.1692 %. They were 5.0824 %, 23.9835%, 32.7484%, <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$22.8878 \%, 11.6961 \%$</tex> and 2.4689 %, respectively. This study provides a novel approach to forecasting crossword puzzle games and serves as a reference for similar game predictions.