Analysis of the Wordle data based on a time-series prediction model
DOI:
https://doi.org/10.54097/hset.v57i.10005Keywords:
Time series prediction, Machine learning, decision tree, Regression decision tree classification, K-means clustering.Abstract
Wordle Is a popular word game daily provided by the New York Times. In this paper, we make a further data analysis on Wordle by using the time-series model. First, a time series model was built to predict and test the results, and the correlation of word properties with the degree of difficulty was analyzed. Second, we build multiple multivariate regression models, take the percentages of 1,2,3,4,5,6, and X as output variables, find the relationship between word attributes and the percentage of each attempt and make predictions. Finally, words were classified by difficulty based on the extracted attributes and eerie by the resulting model and evaluated for accuracy.
Downloads
References
Wang Yan. Application of time series analysis [M]. Beijing: China Renmin University Press 2005.
Xu Weichao. Review of correlation coefficients [J]. Journal of Guangdong University of Technology,2012,29(3):12-17.
Zhou Zhihua. Machine Learning [M]. Tsinghua University Press, 2016.
Draper, N.R. and Smith, H. Applied Regression Analysis. Wiley Series in Probability and Statistics. 1998.
Meng Q . LightGBM: A Highly Efficient Gradient Boosting Decision Tree. 2018.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
