Is Linear Regression Still a Good Prediction Method?

Forecasting stock prices is a challenge due to the non-stationary nature of price time series and the noisy data inherent in these price sequences. Linear regression was a frequently used prediction method, but recent advancements in computing technologies have given rise to more sophisticated approaches like Long Short-Term Memory (LSTM), Artificial Neural Networks (ANN), Recurrent Neural Networks (RNN), etc.

Does the linear regression method still have its place amongst these advanced techniques?

Reference [1] examines the effectiveness of the linear regression method by applying it to a set of US stocks, using it for predicting closing prices and 10-day moving averages. The authors pointed out,

The effectiveness of our models was clearly demonstrated through their exceptional performance metrics. Both Model 1 and Model 2 exhibited strong predictive capabilities, with low RMSE values indicating minimal prediction errors. Additionally, their low MAE (Mean Absolute Error) values showcased the accuracy of our forecasts. R-squared values, which measure the proportion of variance in the dependent variable that’s predictable from the independent variables, were also notably high. These robust performance metrics highlight the models’ ability to provide accurate predictions for stock prices and Exponential Moving Averages (EMA_10), making them valuable tools for traders and investors in navigating the stock market with confidence. Our proposed trading strategy strategy not only yielded impressive profits but also notably minimized risk.

In brief, linear regression is still an effective prediction method. It remains a viable method due to its

• Simplicity, and interpretability;

• Adaptability to both linear and non-linear relationships,

• Efficiency with smaller datasets,

• Ability to mitigate excessive overfitting.

When designing a trading system, our goal is always to keep it simple. This approach is likely to enhance the robustness of our system. Therefore we opt for linear regression as our tool of choice.

Let us know what you think in the comments below.

References

[1] S. Sanapala, V. A. Reddy, S. Sinha Choudhury, V. V. Akshaya and V. Maheedhar Varma, Optimising Trading Strategies using Linear Regression on Stock Prices, 2023 International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering (RMKMATE), Chennai, India, 2023, pp. 1-6, doi: 10.1109/RMKMATE59243.2023.10368702.