Prediction of English Teacher Career Development Based on Data Mining and Time Series Model

Abstract

With the gradual growth of the teaching profession, the teaching profession is facing new trends in reform and development, and the same dilemma exists for English teachers’ career development and planning. To this end, the study first uses a modified K-means clustering method to cluster and analyse the factors affecting English teachers’ professional development, forming a system of indicators on English teachers’ professional development. The Long Short-Term Memory (LSTM) network employed the time-series features to create a time-series model, and the Support Vector Machine (SVM) was used to forecast the course of English teachers’ career development. To assess the current career status of English teachers and their impact on people and organizations, this study proposes a career prediction model for English teachers. This model utilizes data mining and time series modeling to provide accurate predictions. In accordance with the experimental findings, the precision of the upgraded K-Means model was 98.58%, and the error between the projected sample data and the actual sample data for the training of the trend prediction model for English teachers’ career growth was 0.032. It was able to accurately predict teachers’ career development and explore the specific factors affecting English teachers’ career development, so as to solve the problems in teachers’ career development.