A Comparative Analysis of Deep Learning and Traditional Statistics for Stock Price and Return Forecasting
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Purpose: This study aims to present a comparative analysis of various statistical, machine learning, and deep learning models for predicting stock prices and returns across sectors on the Indonesian Stock Exchange. Design/methodology/approach: The research analyzes two indexes and eight prominent companies from different sectors using historical data of fundamental, technical indicators, economic factors, analyst recommendation, and social media sentiment during period of 2012-2022. Models such as ARIMA, SARIMA, VAR, Random Forests, GBM, SVM, ANNs, RNNs, and LSTM are applied. Findings: The results indicate that the efficacy of forecasting models varies with the sector and the time scale. ANNs and RNNs outperform for daily forecasts, while VAR is more effective for quarterly and yearly forecasts. Traditional statistical models like VAR and SARIMA are effective in the finance sector for daily and yearly forecasts due to stability and predictability. Machine learning models like GBM and ANN perform better in the mining and infrastructure sectors, which face abrupt changes from external factors. Deep learning models excel in sectors like consumer goods and trade for yearly forecasts, capturing intricate, evolving patterns. Despite the strengths of deep learning models in specific stocks, no single model universally excels across all contexts. Research limitations/implications: The study is limited to the Indonesian Stock Exchange. Further research could expand the scope to other markets. The effectiveness of predictive tools may be reduced in markets with significant information gaps, affecting their accuracy in less efficient markets. Originality/value: This research fills a gap by systematically comparing traditional statistical methods, machine learning, and deep learning models across multiple sectors and timeframes, providing valuable insights into strategic model selection for stock price and return forecasting.
Abstract
Purpose: This study aims to present a comparative analysis of various statistical, machine learning, and deep learning models for predicting stock prices and returns across sectors on the Indonesian Stock Exchange. Design/methodology/approach: The research analyzes two indexes and eight prominent companies from different sectors using historical data of fundamental, technical indicators, economic factors, analyst recommendation, and social media sentiment during period of 2012-2022. Models such as ARIMA, SARIMA, VAR, Random Forests, GBM, SVM, ANNs, RNNs, and LSTM are applied. Findings: The results indicate that the efficacy of forecasting models varies with the sector and the time scale. ANNs and RNNs outperform for daily forecasts, while VAR is more effective for quarterly and yearly forecasts. Traditional statistical models like VAR and SARIMA are effective in the finance sector for daily and yearly forecasts due to stability and predictability. Machine learning models like GBM and ANN perform better in the mining and infrastructure sectors, which face abrupt changes from external factors. Deep learning models excel in sectors like consumer goods and trade for yearly forecasts, capturing intricate, evolving patterns. Despite the strengths of deep learning models in specific stocks, no single model universally excels across all contexts. Research limitations/implications: The study is limited to the Indonesian Stock Exchange. Further research could expand the scope to other markets. The effectiveness of predictive tools may be reduced in markets with significant information gaps, affecting their accuracy in less efficient markets. Originality/value: This research fills a gap by systematically comparing traditional statistical methods, machine learning, and deep learning models across multiple sectors and timeframes, providing valuable insights into strategic model selection for stock price and return forecasting.
참고문헌 (45)
- Althelaya, K., "Combining deep learning and multiresolution analysis for stock market forecasting", IEEE Access, 9, pp.13099~13111 (2021)[DOI]
- Anderies, A., "Telekom-net : The embeded BI-LSTM and expert konwledge model for stock forecasting and suggestion", ICIC Express Letters, 16(6), pp.679~686 (2022)[DOI]
- Chen, Y., "A novel technical analysis-based method for stock market forecasting", Soft Computing, 22, pp.1295~1312 (2018)[DOI]
- Chun, S. J., "Forecasting the equity risk premium in the Korean stock market : A factor analysis approach", Global Business and Finance Review, 26(4), pp.77~89 (2021)[DOI]
- Da Costa Filho, A. E., "A Macroeconomic Perspective on Brazilian FX Swaps", Brazilian Review of Econometrics, 41(1), pp.101~124 (2022)[DOI]
- De Jong, P., "Predictive modeling applications in actuarial science: Volume I:predictive modeling techniques", pp.427~448 (2014), Cambridge University Press
- Diaz, J. M., "ITTSAE : A set of interactive software tools for time series analysis education", IEEE Control Systems, 36(3), pp.112~120 (2016)[DOI]
- Dombi, J., "Studies in computational intelligence (Vol. 814)", pp.135~165 (2021), Springer Science and Business Media Deutschland GmbH
- Erasmus, E. G., "Captial market indicators and economic growth in Nigeria", European Journal of Accounting, Finance and Investment, 7(4), pp.1~14 (2021)
- Eun Jung Go, "Analysis of the current and future of the artificial intelligence in financial industry with big data techniques", Global Business and Finance Review, 25(1), pp.102~117 (2020)
- Garcia, R. T., "Can accounting-based and market-based indicators predict changes in the risk rating of Brazilian banks?", Revista Brasileira de Gestao de Negocios, 21(1), pp.3968~ (2019)[DOI]
- Gavurova, B., "Relations between infrastructure innovations and tourism spending in developed countries : A macroeconomic perspective", Technological and Economic Development of Economy, 27(5) (2021)[DOI]
- Herwindiati, D. E., "A comparison of two deep learning models on the stock exchange predictions", International Journal of Advances in Soft Computing and Its Applications, 15(2), pp.225~234 (2023)[DOI]
- Jiang, W., "Applications of deep learning in stock market prediction : Recent progress", Expert Systems with Applications, 184, pp.115537~ (2021)[DOI]
- Kannadhasan, S., "Big data, cloud computing and IoT:Tools and applications", pp.81~91 (2023), CRC Press
- LaVan, H., "Attitudes of employees in green companies regarding CSR communication", International Journal of Manpower, 43(6) (2022)[DOI]
- Lee, H. J., "Investor sentiment, cross-sectional stock returns, and short-sales : Evidence from Korea", Global Business and Finance Review, 28(3), pp.117~135 (2023)[DOI]
- Liu, L., "Forecasting stock market volatility : The role of technical variables", Economic Modelling, 84, pp.55~65 (2020)[DOI]
- Mukherjee, S., "Stock market prediction using deep learning algorithms", CAAI Transactions on Intelligence Technology, 8(1), pp.82~94 (2023)[DOI]
- Nedeltcheva, G., "Forecasting stock market trends", Economic Quality Control, 30(1), pp.21~38 (2015)[DOI]
- Oliver-Márquez, F. J., "Measuring financial knowledge : a macroeconomic perspective", International Economics and Economic Policy, 18(1) (2021)[DOI]
- Omar, A., "Stock market forecasting using the random forest and deep neural network models before and during the COVID-19 period", Front. Environ. Sci, 10 (2022)[DOI]
- Patel, H. R., "Challenges and applications for implementing machine learning in computer vision", pp.119~135 (2019), IGI Global
- Paul, M. K., "A comparative study of deep learning Algorithms for forecasting Indian stock market trends", International Journal of Advanced Computer Science and Applications, 14(10), pp.932~941 (2023)[DOI]
- Sinaga, F., "Stock Trend Prediction using SV-kNNC and SOM", 2019 Fourth International Conference on Informatics and Computing (ICIC), pp.1~5 (2019)
- Rifa'i, A., "Optimized fuzzy backpropagation neural network using genetic algorithm for predicting indonesian stock exchange composite index", International Conference on Electrical Engineering, Computer Science and Informatics (EECSI), pp.195~199 (2019), IEEE
- Sezer, O. B., "Financial time series forecasting with deep learning : A systematic literature review : 2005-2019", Applied Soft Computing, 90, pp.106181~ (2020)[DOI]
- Shahi, T. B., "Stock price forecasting with deep learning : A comparative study", Mathematics, 8(9), pp.1441~ (2020)[DOI]
- Shanthamallu, U. S., "Synthesis lectures on signal processing", pp.43~57 (2022), Springer Nature
- Sharma, S., "Evidence of price discovery on the Indonesian stock exchange", Economic Modelling, 83, pp.2~7 (2019)[DOI]
- Sinaga, F., "Stock trend prediction using SV-kNNC and SOM", IEEE, ~ (2019)
- Sonkavde, G., "Forecasting stock market prices using machine learning and deep learning models : A systematic review, performance analysis and discussion of implications", International Journal of Financial Studies, 11(3), pp.94~ (2023)[DOI]
- Sonkavde, G., "Forecasting stock market prices using machine learning and deep learning models : A systematic review, performance analysis and discussion of implications", International Journal of Financial Studies, 11(3), pp.94~ (2023)[DOI]
- Sood, S., "AI and emotional intelligence for modern business management", pp.241~253 (2023), IGI Global
- Sulistio, B., "Energy sector stock price prediction using the CNN, GRU & LSTM hybrid Algorithm", ICCoSITE 2023 - international conference on computer science, information technology and engineering: Digital transformation strategy in facing the VUCA and TUNA era, pp.178~182 (2023), IEEE
- Suparno, E., "Group identification in Indonesian stock market", Journal of Physics: Conference Series, 739 (2016)[DOI]
- Syukur, A., "Prediction of LQ45 index in Indonesia stock exchange : A comparative study of machine learning techniques", International Journal of Intelligent Engineering and Systems, 14(1), pp.453~463 (2020)[DOI]
- Thompson, N. C., "Deep learning's diminishing returns : The cost of improvement is becoming unsustainable", IEEE Spectrum, 58(10), pp.50~55 (2021)[DOI]
- US-EPA, "Greenhouse gas(GHG)emissions and removals", United States Environmental Protection Agency, ~ (2021)
- Vasyaeva, T., "Stock prices forecasting with LSTM networks", Communications in Computer and Information Science (2019)[DOI]
- Verma, S., "Stock market forecasting with different input indicators using machine learning and deep learning techniques : A review", Engineering Letters, 31(1), pp.213~229 (2023)
- Wang, S., "Research on data mining and investment recommendation of individual users based on financial time series analysis", International Journal of Data Warehousing and Mining, 16(2), pp.64~80 (2020)[DOI]
- Wu, W., "Stock Prediction Methodology using Artificial Neural Network : Application in Tesla stock price", BCP Business & Management, 38 (2023)[DOI]
- Yamen, A., "The impact of public governance perception on the quality of financial reporting", Economic Research-Ekonomska Istrazivanja, 36(3) (2023)[DOI]
- Yao, X., "Search methodologies: Introductory tutorials in optimization and decision support techniques", pp.477~518 (2014), Springer