Skill Gap Analysis Through Time Series Forecasting: A Literature Survey on LSTM and Related Models

This literature review explores the use of Long Short-Term Memory (LSTM) networks to analyze, identify, and predict skill gaps in colleges catering to the needs of the industry. The rapid development of technology and the requirements from the industry are changing and colleges are required to update their curriculum to ensure that the students are made industry-ready. LSTM, a form of Recurrent Neural Networks (RNN),has gained prominence in predicting this gap with sequential data and also forecasting future trends with time series data. This paper examines the research of leveraging the LSTM to analyze the skill gaps in colleges and thereby align the educational outcomes.