International Journal of Financial Technology Perspective

International Journal of Financial Technology Perspective

The role of market timing in the development of financial products

Authors
Sanaz Faridi 1
Mahdi Madanchi Zaj 2
Amir Daneshvar 3
Shadi Shahverdiyani 4
1 Department of Financial Management, Science and Research Branch, Islamic Azad University, Tehran, Iran
2 Department of Financial Management, Electronic Branch, Islamic Azad University, Tehran, Iran
3 Department of Information Technology Management, Electronic Branch, Islamic Azad University, Tehran, Iran
4 Department of Financial Management, Human Sciences Faculty, Islamic Azad University, Shahr- e- Qods branch Tehran, Iran
Abstract
Research into the development of new financial products in the capital market has received much attention over the decades and one of the financial implications in the capital market is the use of new models in predicting market trends to control risk and increase returns. Which can also be used as a market timer, in this regard, the market timer by adding the market timing system to the process of but since successful market timing strategies depend on superior forecasting ability, Therefore, in this paper, using the market timing approach of new products in the field of capital market trend forecasting to control risk and increase the return on investment presented. for this work with a homogeneous and heterogeneous two-level ensemble learning method (HHEL) to provide the buy, hold and sell signal and market forecast are based on the basic characteristics, technical characteristics and time series of each company's return in the 10 days leading up to the current day. Based on this, 208 companies were selected as active companies between 1390 and 1399. The data of the first 5 years have been used using the begging method to teach the model and the model has been optimized using the genetic algorithm (GA) to increase accuracy and efficiency, and to test the proposed model in stock portfolio to determine options The investment is used and the genetic algorithm (GA) is used as stock portfolio optimization based on maximizing stock portfolio returns and minimizing investment portfolio risk, and finally the return and portfolio risk obtained are compared with the buy and hold strategy. The results showed that the proposed prediction model compared to other comparative models with Accuracy 92.34% and Sensitivity 83.88% and Specificity 92.92 has the highest accuracy and reliability compared to other comparative models. And the average error in trend classification by the homogeneous and heterogeneous two-level combined model is less than other comparative models. Also, the proposed model for daily portfolio formation and daily weighting of selected stocks (HHEL + GA) Compared to buying and maintaining strategies to increase with 63% hit and 70 times higher return on investment and Sharp ratio 14 times higher without commission and having a portfolio with controlled risk help reduce investment risk and maintain portfolio value determining and allocating investment options can determine the time of timely entry and exit.
Keywords
financial product
portfolio optimization
market timing
Ensemble machine learning model
  • Amiri, Maghsoud, Hadadian, Hamid Reza, Zandieh, Mustafa, & Raeeszadeh. (2016). Provide smart trading model in financial markets based on genetic algorithm, fuzzy logic and neural network. Financial Engineering and Securities Management, 27, 33-52.
  • Andersen, K., & Glenn, P. (2014). Portfolio Preservation During Severe Market Corrections: A Market Timing Enhancement to Modern Portfolio Theory.
  • Bollerslev T,Marrone J, Xu L, Zhou H (2014) Stock return predictability and variance risk premia: statistical inference and international evidence. J Financ Quant Anal 49(3):633–661
  • Duarte, J. (2009). Market Timing for Dummies. John Wiley & Sons.
  • Fama, E. F. (1970). Efficient capital markets: A review of theory and empirical work. The journal of Finance, 25(2), 383-417.
  • Jobst, N. J., Horniman, M. D., Lucas, C. A., & Mitra, G. (2001). Computational aspects of alternative portfolio selection models in the presence of discrete asset choice constraints. Quantitative finance, 1(5), 489.
  • Jothimani, D., & Yadav, S. S. (2019). Stock trading decisions using ensemble-based forecasting models: a study of the Indian stock market. Journal of Banking and Financial Technology, 3(2), 113-129.‏
  • Kim JH, Shamsuddin A, Lim KP (2011) Stock return predictability and the adaptive markets hypothesis: evidence from century-long U.S. data. J Empir Finance 18(5):868–879
  • Markowitz, H. (1952). The utility of wealth. Journal of political Economy, 60(2), 151-158.
  • Mascio, D. A., Fabozzi, F. J., & Zumwalt, J. K. (2021). Market timing using combined forecasts and machine learning. Journal of Forecasting, 40(1), 1-16.‏
  • Mascio, D. A., Fabozzi, F. J., & Zumwalt, J. K. (2021). Market timing using combined forecasts and machine learning. Journal of Forecasting, 40(1), 1-16.‏
  • Mousavi Anzahi, Seyed Majid, Niko Maram, & Hashem. (2020). Designing a model for determining stock trading strategies with a futures-based approach, fundamental analysis, feature engineering and machine learning algorithms. Financial Engineering and Securities Management, 11 (45), 499-517.
  • Paiva, F. D., Cardoso, R. T. N., Hanaoka, G. P., & Duarte, W. M. (2019). Decision-making for financial trading: A fusion approach of machine learning and portfolio selection. Expert Systems with Applications, 115, 635-655.
  • Phan DHB, Sharma SS, Narayan PK (2015) Stock return forecasting: some new evidence. Int Rev Financ Anal 40:38–51
  • Potters, M., Bouchaud, J. P., & Laloux, L. (2005). Financial applications of random matrix theory: Old laces and new pieces. arXiv preprint physics/0507111.‏
  • Qasemian, & Rudpashti Guide. Knowledge of financial astrology and its functions in market analysis. Investment Knowledge, 5 (20), 277-296.
  • Qin, Y., Pan, G., & Bai, M. (2020). Improving market timing of time series momentum in the Chinese stock market. Applied Economics, 1-15.
  • Qiu, Y., Yang, H. Y., Lu, S., & Chen, W. (2020). A novel hybrid model based on recurrent neural networks for stock market timing. Soft Computing, 1-18.‏
  • Raffinot, T., & Benoît, S. (2018). Investing through economic cycles with ensemble machine learning algorithms. Available at SSRN 2785583.
  • Rai, R., Hosseini, S., & Seyed Farhang. (2015). Comparison of sales returns based on technical indicators and fuzzy logic and the combined method of genetic algorithm-fuzzy logic. Financial Engineering and Securities Management, 6 (24), 1-14.
  • Sadeghi, A., Daneshvar, A., & Zaj, M. M. (2021). Combined ensemble multi-class SVM and fuzzy NSGA-II for trend forecasting and trading in Forex markets. Expert Systems with Applications, 185, 115566.
  • Tehrani Reza, & Abbasid Vahid ,2008. Application of artificial neural networks in stock trading scheduling: with a technical analysis approach.
  • Tehrani, Hindijanizadeh, & Norouzian Lekvan. (2014). Provide a new approach to active portfolio management and smart stock trading with an emphasis on feature selection. Investment Knowledge, 4 (13), 107-126.
  • Wang, W., Li, W., Zhang, N., & Liu, K. (2020). Portfolio formation with preselection using deep learning from long-term financial data. Expert Systems with Applications, 143, 113042.‏
  • Xiao JH, Zhu XH, Huang CX, Yang XG, Wen FH, Zhong MR (2019) A new approach for stock price analysis and prediction based on SSA and SVM. Int J Inf Technol Decis Mak 18(1):287–310
  • Zhang J, Teng YE, Chen W (2019) Support vector regression with modified firefly algorithm for stock price forecasting. Appl Intell 49(5):1658–1674.
International Journal of Financial Technology Perspective
Volume 2, Issue 4
Spring 2025
Pages 63-82