Temporal Relational Ranking for Stock Prediction

Abstract

Stock prediction aims to predict the future trends of a stock in order to help investors to make good investment decisions. Traditional solutions for stock prediction are based on time-series models. With the recent success of deep neural networks in modeling sequential data, deep learning has become a promising choice for stock prediction.However, most existing deep learning solutions are not optimized towards the target of investment, i.e., selecting the best stock with highest expected revenue. Specifically, they typically formulate stock prediction as a classification (to predict stock trend) or a regression problem (to predict stock price). More importantly, they largely treat the stocks as independent of each other. The valuable signal in the rich relations between stocks (or companies), such as two stocks are in the same sector and two companies have a supplier-customer relation, is not considered.In this work, we contribute a new deep learning solution, named Relational Stock Ranking (RSR), for stock prediction. Our RSR method advances existing solutions in two major aspects: 1) tailoring the deep learning models for stock ranking, and 2) capturing the stock relations in a time-sensitive manner. The key novelty of our work is the proposal of a new component in neural network modeling, named Temporal Graph Convolution, which jointly models the temporal evolution and relation network of stocks. To validate our method, we perform back-testing on the historical data of two stock markets, NYSE and NASDAQ. Extensive experiments demonstrate the superiority of our RSR method. It outperforms state-of-the-art stock prediction solutions achieving an average return ratio of 98% and 71% on NYSE and NASDAQ, respectively.

LSTM with Wavelet Transform Based Data Preprocessing for Stock Price Prediction

“…This method first employed the ARIMA model to filter out the linear trend in the data and then passed the residual value to the LSTM. FULI FENG et al [16] proposed a deep learning program for Relational Stock Ranking (RSR). The Temporal Graph Convolution method was brought in to simulate the temporal evolution of the stock and the relational network, and the solution was implemented using the LSTM network.…”

Ultimate Prediction of Stock Market Price Movement

“…To predict future value or behavior from those observations or patterns it will then iteratively learn from data, unlike typical computer programs. The purpose of machine learning is to program computers to use sample data as an experience or model and use the patterns of this data to predict the future based on that data (Nayak et al, 2016;Feng et al, 2019). Machine Learning not only deals with database problems but is also an application of artificial intelligence (AI).…”

Recommending System for Penny Stock Trading

“…In [4], a contemporary model of deep learning solution was introduced as RSR (Relational Stock Ranking) in the case of the stock prediction. The two key aspects that are integral to the plans are about customizing the deep learning models for enhancing the stock ranking and towards capturing the stock relations across the time-sensitive conditions.…”

“…Based on the insights from the experimental analysis using the set of financial articles and the related stock movement, the inferences in the study are made by the model. The other contribution "Temporal Relational Ranking for Stock Prediction (TRRSP)" [10] is a contemporary contribution of the recent past, which has intended to resolve the constraints observed in other contemporary models. The method TRRSP is a machine learning strategy that considering the temporal validity of the features in given training corpus.…”

“…In Figure 1, the graph is plotted among precision and four folds for the proposed RSPST method and contemporary TRRSP method. The average standard deviation (ASD) of precision for the RSPST model is (0.9243±0.0015) and for contemporary TRRSP model [10] is (0.92185±0.0026). From the statistics, it is evinced that the proposed model RSPST model performs better when compared to other contemporary TRRSP model.…”