Prediction of Wordle report distribution results based on PSO-LBGM prediction model

Yuqing Zhang

doi:10.54097/hset.v68i.12081

Authors

Yuqing Zhang

DOI:

https://doi.org/10.54097/hset.v68i.12081

Keywords:

Number of people distribution results, Prediction Model, PSO, LightGBM.

Abstract

Accurate prediction of Wordle report headcount distribution is an important reference for Wordle's later word difficulty setting to expand the number of players. In order to increase the number of purchased products, the prediction model of the number of people distribution results is constructed by using Lightweight Gradient Boosting Machine (LightGBM), and PSO is used to optimize the hyperparameters of the LightGBM model. The historical data were preprocessed and the word attributes were extracted using unique thermal coding to build prediction models based on PSO-LightGBM, LightGBM and LSTM. The results show that the mean absolute percentage (MAPE) of the training and test sets predicted by PSO-LightGBM for (1, 2, 3, 4, 5, 6, X) is 0.531%, 0.410%, respectively. and the model was more accurate in predicting the number distribution results than LightGBM and LSTM models.

Downloads

Download data is not yet available.

References

Li, Renyuan,Zhu,Shenglong. Playing Mastermind with Wordle’s Feedback [D]. Mathematics, Nanjing University, China, 2022.

Yin XY, Wang XY, Shi A, et al. Feasibility study on predicting cotton yield based on gray theory and time series model [J]. Cotton Science, 2021.

Luo J-P, Zhang Y-Z, Yang S-B. Bus journey time prediction based on PSO-LightGBM [J]. Transportation Engineering, 2023.

Wang, Meixia. Research and application of time series forecasting model based on conjugate gradient method and optimization theory [D]. Yanshan University, 2017.

Wang S.F., Bao C.C. Research on the application of intelligent algorithms in grid load forecasting [J]. Journal of Anhui University of Engineering, 2021.

Liu, ChaoLin. Using Wordle for Learning to Design and Compare Strategies [D]. National Chengchi University, Taiwan, 2022.

Lokshtanov, Daniel. Wordle Is NP-Hard [D]. University of California, Santa Barbara, United States, 2022.

De Silva, Nisansa. Selecting Optimum Seed Words for Wordle using Character Statistics [D]. Moratuwa University, 2022.

Wang Mingfeng. Research on text clustering algorithm based on particle swarm optimization algorithm (PSO) [D]. Guangdong University of Technology, 2020.

Zong Min, Yang Yuqun, Xu Gang. A diversity-driven adaptive particle swarm optimization algorithm [J]. Journal of Nanchang University (Science Edition), 2022.

Jiang Qirong, Wei Y, Gao Xian Song et al. Short-term electric load forecasting by combined LSTM-LightGBM model [J]. China Plant Engineering, 2023.

hang Wei, Yu Chiongbian Shibin et al. multi-feature short-term power load forecasting based on VMD-LSTM-LightGBM [J]. Southern Power Grid Technology, 2023.