Stock Prediction via Time Series Clustering and Image Feature Extraction

Stock time series has the characteristics of high dimensionality and nonlinearity, which brings great challenges to stock forecasting. Aiming at the impact of stock correlation and the prediction information contained in stock image features, we propose a hybrid model based on time series and image feature extraction. Firstly, the Kmeans algorithm is used for stock clustering, where the most correlated stocks are found. Secondly, a convolutional autoencoder (CAE) is applied to extract stock price image features. Finally, the stock technical data and image features are respectively input into the double-layer long short-term memory network (LSTM) to predict the stock price of the next trading day. The empirical research results on financial sector in China's stock market show that the proposed hybrid model can obtain a competitive result compared with other existing methods.