[1I3-GS-2] Machine learning: Market analysis

[1I3-GS-2-05] A study of encoder decoder model using LSTM for medium and long term economic indicator forecast

〇Takuya Nakaoka¹, Shoichi Urano¹ (1. Meiji University)

Keywords:Economic indicator, Neural Network, Time series data analysis

The purpose of this paper is to predict economic indicators with high accuracy and to grasp the characteristics of economic trends as one of the technical analysis for measuring business trends used as a reference for management policies. Up to now, economic indicator forecasts have been performed in various ways, and the accuracy has been improved. Therefore, this paper proposes a method of predicting economic indicators using encoder decoder model based on LSTM (Long Short Term Memory), which is a type of RNN (Recurrent Neural Network), as a forecasting method that can be used to forecast medium and long term economic indicators, confirms the effectiveness of the prediction method by simulation.