Journal Screenshot

International Journal of Academic Research in Economics and Management Sciences

Open Access Journal

ISSN: 2226-3624

A Hybrid AR and Leading Technical Indicator Framework for TSMC Stock Price Prediction

Liang Ying Wei

http://dx.doi.org/10.6007/IJAREMS/v15-i4/29117

Open access

Accurately predicting stock price movements remains a challenging task due to the inherent volatility of financial markets and the complex temporal dependencies of financial time series. This study uses the stock price data of Taiwan Semiconductor Manufacturing Company (TSMC), one of the world's leading semiconductor manufacturers, as the basis for stock price prediction. Daily closing prices from 2016 to 2025 were collected and divided into training and testing datasets on a yearly basis. To improve prediction accuracy, an autoregressive model of order one (AR(1)) and technical indicators were combined with three machine learning algorithms: Random Forest (RF), Neural Network (NN), and Support Vector Regression (SVR). The performance of each prediction model was evaluated using Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). The prediction errors generated by the different models were analyzed and compared using the testing dataset for each year. The experimental results indicate that TSMC's stock price exhibited significant upward trends and increased volatility during the period from 2020 to 2025, mainly due to the impacts of the COVID-19 pandemic, the U.S.–China trade war, and the rapid growth of the artificial intelligence (AI) industry. Among the six prediction models, the proposed AR(1)-TI-NN model, which integrates AR(1), technical indicators, and a neural network, achieved the best overall prediction performance. It produced the lowest average MAE (6.49995) and RMSE (10.06181) and achieved the best prediction accuracy in 18 out of 20 experimental comparisons. These findings demonstrate that incorporating technical indicators into the AR(1)-NN framework significantly improves stock price prediction accuracy and provides a reliable reference for investors and financial analysts in investment decision-making.

Bayer, J. (2015). Learning sequence representations [Doctoral dissertation, Technical University of Munich].
Bayer, F. M., Bayer, D. M., & Pumi, G. (2017). Kumaraswamy autoregressive moving average models for double bounded environmental data. Journal of Hydrology, 555, 385–396.
Berry, M. J. A., & Linoff, G. (1997). Data mining techniques: For marketing, sales, and customer support. John Wiley & Sons.
Bollerslev, T. (1986). Generalized autoregressive conditional heteroscedasticity. Journal of Econometrics, 31(3), 307–327.
Boser, B. E., Guyon, I. M., & Vapnik, V. N. (1992). A training algorithm for optimal margin classifiers. In Proceedings of the fifth annual workshop on computational learning theory (pp. 144–152). Association for Computing Machinery.
Box, G. E. P., & Jenkins, G. M. (1976). Time series analysis: Forecasting and control. Holden-Day.
Malkiel, B. G. (2003). The efficient market hypothesis and its critics. Journal of Economic Perspectives, 17(1), 59–82.
Caruana, R., Niculescu-Mizil, A., Crew, G., & Ksikes, A. (2004). Ensemble selection from libraries of models. In Proceedings of the 21st International Conference on Machine Learning (pp. 18–25). Association for Computing Machinery.
Engle, R. F. (1982). Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation. Econometrica, 50(4), 987–1008.
Chong, E., Han, C., & Park, F. C. (2017). Deep learning networks for stock market analysis and prediction: Methodology, data representations, and case studies. Expert Systems with Applications, 83, 187–205.
Fayyad, U. M., Shapiro, G. P., Smyth, P., & Uthurusamy, R. (Eds.). (1996). Advances in knowledge discovery and data mining. AAAI Press/MIT Press.
Box, G. E. P., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time series analysis: Forecasting and control (5th ed.). John Wiley & Sons.
Hippert, H. S., Pedreira, C. E., & Souza, R. C. (2001). Neural networks for short-term load forecasting: A review and evaluation. IEEE Transactions on Power Systems, 16(1), 44–51.
Huarng, K. H. (2001). Effective lengths of intervals to improve forecasting in fuzzy time series. Fuzzy Sets and Systems, 123(3), 387–394.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
Chang, P. L., & Tsai, C. T. (2000). Evolution of technology development strategies for Taiwan’s semiconductor industry: Formation of research consortia. Industry and Innovation, 7(2), 185–197.
Parker, D. B. (1985). Learning-logic: Casting the cortex of the human brain in silicon (Technical Report No. TR-47). Center for Computational Research in Economics and Management Science, Massachusetts Institute of Technology.
Cont, R. (2001). Empirical properties of asset returns: Stylized facts and statistical issues. Quantitative Finance, 1(2), 223–236.
Sutskever, I. (2012). Training recurrent neural networks [Doctoral dissertation, University of Toronto].
Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654–669.
Ho, T. K. (1995). Random decision forests. In Proceedings of the Third International Conference on Document Analysis and Recognition (Vol. 1, pp. 278–282). IEEE.
Zhang, G. P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50, 159–175.

Wei, L. Y. (2026). A Hybrid AR and Leading Technical Indicator Framework for TSMC Stock Price Prediction. International Journal of Academic Research in Economics and Management Sciences, 15(4), 252–265.