Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ResNLS: An Improved Model for Stock Price Forecasting

Yuanzhe Jia, Ali Anaissi, Basem Suleiman

TL;DR

The experimental results show that the trading strategy based on predictions from ResNLS‐5 can successfully mitigate losses during declining stock prices and generate profits in the periods of rising stock prices.

Abstract

Stock prices forecasting has always been a challenging task. Although many research projects try to address the problem, few of them pay attention to the varying degrees of dependencies between stock prices. In this paper, we introduce a hybrid model that improves the prediction of stock prices by emphasizing the dependencies between adjacent stock prices. The proposed model, ResNLS, is mainly composed of two neural architectures, ResNet and LSTM. ResNet serves as a feature extractor to identify dependencies between stock prices, while LSTM analyzes the initial time series data with the combination of dependencies, which are considered as residuals. Our experiment reveals that when the closing price data for the previous 5 consecutive trading days is used as input, the performance of the model (ResNLS-5) is optimal compared to those with other inputs. Furthermore, ResNLS-5 demonstrates at least a 20% improvement over current state-of-the-art baselines. To verify whether ResNLS-5 can help clients effectively avoid risks and earn profits in the stock market, we construct a quantitative trading framework for back testing. The result shows that the trading strategy based on ResNLS-5 predictions can successfully mitigate losses during declining stock prices and generate profits in periods of rising stock prices. The relevant code is publicly available on GitHub.

ResNLS: An Improved Model for Stock Price Forecasting

TL;DR

The experimental results show that the trading strategy based on predictions from ResNLS‐5 can successfully mitigate losses during declining stock prices and generate profits in the periods of rising stock prices.

Abstract

Stock prices forecasting has always been a challenging task. Although many research projects try to address the problem, few of them pay attention to the varying degrees of dependencies between stock prices. In this paper, we introduce a hybrid model that improves the prediction of stock prices by emphasizing the dependencies between adjacent stock prices. The proposed model, ResNLS, is mainly composed of two neural architectures, ResNet and LSTM. ResNet serves as a feature extractor to identify dependencies between stock prices, while LSTM analyzes the initial time series data with the combination of dependencies, which are considered as residuals. Our experiment reveals that when the closing price data for the previous 5 consecutive trading days is used as input, the performance of the model (ResNLS-5) is optimal compared to those with other inputs. Furthermore, ResNLS-5 demonstrates at least a 20% improvement over current state-of-the-art baselines. To verify whether ResNLS-5 can help clients effectively avoid risks and earn profits in the stock market, we construct a quantitative trading framework for back testing. The result shows that the trading strategy based on ResNLS-5 predictions can successfully mitigate losses during declining stock prices and generate profits in periods of rising stock prices. The relevant code is publicly available on GitHub.
Paper Structure (12 sections, 4 equations, 10 figures, 5 tables)

This paper contains 12 sections, 4 equations, 10 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Preliminary
  4. Methodology - ResNLS
  5. Experimental Results
  6. Dataset
  7. Training Procedure
  8. Evaluation Metrics
  9. Exploratory Data Analysis
  10. Model Comparison
  11. Back Testing
  12. Conclusion

Figures (10)

  • Figure 1: The structure of the LSTM neuron.
  • Figure 2: Research ideas of ResNLS.
  • Figure 3: Structure of ResNLS.
  • Figure 4: Prediction loss of ResNLSs with different inputs. For each sub-graph: (a) “n” equals to 3; (b) “n” equals to 5; (c) “n” equals to 10; (d) “n” equals to 20; (e) “n” equals to 40; (f) “n” equals to 60.
  • Figure 5: Prediction results of the SSE Composite Index from LSTM.
  • ...and 5 more figures