Importance-Weighted Distance Aware Stocks Trend Prediction

A great deal of work has been proposed on the application of neural networks (NN) to stock price prediction. Since correlation between stocks has been proven to be crucial in stock price prediction, researchers presented plenty of clustering algorithms to retrieve similar stocks. However, most of the existing clustering approaches have the issue of information-loss and may sometimes offer an oversized cluster, both of which will cause a drop of prediction performance. In this paper, we propose a multidimensional similarity-calculating function to seek out relevant stocks, the technical indicators of which are then fed into NN to predict the stocks’ price trend. Evaluation is carried out on two stock indexes and 18 individual stocks, demonstrating that the proposed model provides a promising alternative to stock price prediction.

[1]  Yilin Fang,et al.  An Effective Similarity Measure Algorithm for Time Series Based on Key Points , 2016, 2016 8th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC).

[2]  Sahil Shah,et al.  Predicting stock and stock price index movement using Trend Deterministic Data Preparation and machine learning techniques , 2015, Expert Syst. Appl..

[3]  Ömer Kaan Baykan,et al.  Predicting direction of stock price index movement using artificial neural networks and support vector machines: The sample of the Istanbul Stock Exchange , 2011, Expert Syst. Appl..

[4]  Sheng-Hsun Hsu,et al.  A two-stage architecture for stock price forecasting by integrating self-organizing map and support vector regression , 2009, Expert Syst. Appl..

[5]  Ying Wah Teh,et al.  Stock market co-movement assessment using a three-phase clustering method , 2014, Expert Syst. Appl..

[6]  Jiahai Wang,et al.  Financial time series prediction using a dendritic neuron model , 2016, Knowl. Based Syst..

[7]  Charu C. Aggarwal,et al.  Stock Price Prediction via Discovering Multi-Frequency Trading Patterns , 2017, KDD.

[8]  Ching-Hsue Cheng,et al.  A hybrid ANFIS based on n-period moving average model to forecast TAIEX stock , 2014, Appl. Soft Comput..

[9]  Zhang Xiong,et al.  Data Augmentation Based Stock Trend Prediction Using Self-organising Map , 2017, ICONIP.

[10]  Aderemi Oluyinka Adewumi,et al.  Stock Price Prediction Using the ARIMA Model , 2014, 2014 UKSim-AMSS 16th International Conference on Computer Modelling and Simulation.

[11]  Shamik Sural,et al.  Similarity between Euclidean and cosine angle distance for nearest neighbor queries , 2004, SAC '04.

[12]  Byung Ro Moon,et al.  Stock prediction based on financial correlation , 2005, GECCO '05.