Forecasting the Tehran Stock Market by Artificial Neural Network

Objective: Due to the importance of studing the behavior of asset markets, the risk aversion term and its operational calculation has attracted many researchers. The present study intends to examine this issue by considering a portfolio with three assets in the three markets of stock, currency and gold. Therefore, by examining the fluctuations of previous years in the portfolio consisting of three macroeconomic assets , stocks, currency and gold, we can assess the risk aversion of investors in these markets and the causal relationship between these markets and take steps to construct long-term policy goals. Method: To investigate the issue, using a mathematical equilibrium model and dynamic econometric methods, the monthly data of stock markets, currency and gold during the period 1995 to 2018 has been analyzed. Results: Based on the research findings, the amount of risk aversion for the sample size shows that the average risk aversion index of investors in the stock market is higher than the other two markets and this index is the lowest in the gold market. Also, the value-at-risk index of return has a one-way causality and a significant relationship with the degree of risk aversion of investors in all three asset markets. Conclusion: The results of this study of risk aversion and risk value in these markets can help policymakers to better understand the interactions of these markets, control them and eliminat the destabilizing conditions of these markets. Specifically in the case of the Iranian stock market, it can be said that investors are relatively more risk averse to the both gold and foreign exchange markets in the conditions of economic recession and increasing political instability, in other words, stock market investors have less confidence in the exchange and gold markets. The reason is the newness of the stock market compared to the global stock markets and also the longer existence of gold and foreign exchange markets than the emerging stock market in Iran. Also since gold assets have an intrinsic value and the dollar market is supported by a large global economy, Therefore to strengthen the support of the Iranian stock market, it seems improving economic infrastructure, promotion of the conditions of companies in the stock market, increasing government support for competitive condition and prohibition of direct intervention in the stock market are necessary. In addition, due to the complex nature of the stock market and the lack of sufficient public information , the need to inform and increase public awareness for a long-term presence in the stock market seems necessary.

PurposeBusiness Process Management is a systematic way to design, implement and manage business critical processes at different organizational levels to ensure business sustainability. In this paper, we conduct a business process re‐engineering exercise for KBK Securities Co., a small size security company operating in Iranian stock and mercantile market. The company suffered from in‐efficiencies and poor and delayed decision‐making due to poor visibility and complexity with business critical processes.DesignWe employed a semi‐quantitative approach using ELECTRE TRI decision‐making method to identify the business critical processes. Through document analysis, we identified 103 financial and stock market processes to streamlining purposes. We use Multi‐Attribute Utility Theory (MAUT) and ELECTRE TRI methods for first, arriving to a consensus for the imprecise information elicited from a group of departmental managers, and second making a decision‐making to determine the 32 business critical processes out of 103, and third clustering these processes for business process re‐engineering. We make significant contribution in theory by employing a multi criterion decision‐making (MCDM) in the financial sector in the context of a developing economy like Iran.OriginalityWe provide a structured framework along with an off the shelf software tool for practitioners to implement this approach to rationalize the number of processes and subsequently to improve the business critical processes to enhance financial performance in the stock market.FindingsOur findings suggest that company can cut down approximately 68% waste by reducing its business critical processes and spend their available time and resources in growing the business.

PurposeThe purpose of this study, the nonlinear relationship between the real estate market and the stock market was investigated in Iran. For this intent, the monthly data from 2012:4 to 2022:5 is used.Design/methodology/approachIn this study, the quantile-on-quantile estimation method is used, which is a combination of the nonparametric estimation methods and the quantile regression.FindingsThe research results show that, in the low quantiles, the effect of stock market return on the housing market return is negative or zero. In fact, in this situation, the increasing returns in the stock market will shift part of the financial resources of the economy to the market and create stagnation or even negative returns in the housing market. This situation is seen more strongly in some other quantiles, including the 0.25 and 0.75 quantiles; in contrast, the effect of high quantiles of stock market returns is positive on the housing market.Originality/valueIt seems that the demand in the housing market increase in a situation where the returns of the stock market are growing, and the market is in a bullish condition, and this causes an increase in the price and returns in this market. In addition, the results show that the effect of stock market returns on capital market returns is asymmetric and nonlinear.

Background/Objectives: The Coronavirus disease in 2019 (COVID-19) was first seen in Wuhan (capital of Hubei, Chain), and has since spread throughout the world, resulting in the World Health Organisation (WHO) declaring the 2019–20 coronavirus a pandemic. Its ongoing spread has resulted in a standstill of the world’s economy, total lockdown in some counties, closedown of business and firms globally. As of 25th Mar 2020, 11:00 am GMT, a total of 491,280 cases were reported globally. The evolution of COVID-19 and its economic impact on the regional financial markets are highly uncertain, which makes it difficult for legislators to formulate a suitable macroeconomic strategy response.Methods: To ascertain the possible economic impact of COVID-19 globally, this study examines the effect of COVID-19 on major stocks indices across the globe. Using a random sampling technique, we selected thirty (30) world stock market indices in different countries infected with COVID-19 from 31st Dec 2019 to 25th Mar 2020. However, not like a high percentage of previous studies that focus on the regional stock market, we examine the information on daily reported COVID-19 cases and stock market fluctuation over thirty stock market indices that houses the stock prices of several countries around the globe. Also, we estimate the monetary loss within the period, project the future surge of this pandemic on the stock market and outline some portfolio allocation strategies to help the investor hedge against investment risk. Findings: The experimental results in this study show that even a controlled outbreak of the COVID-19 can significantly influence the world’s economy in both the short-term and longterm. Our obtained results of COVID-19 associated economic loss echoed in stock prices movements advise that the cost can escalate severely and quickly into global economic stress. Hence, we conclude by outlining some measure that might help investors hedge against such risk using portfolio allocation strategies. Keywords: Coronavirus; COVID-19; Stock market; stocks price; pandemic; machine-learning; economic impact of COVID-19

Analysis of share prices and stock market indexes has actually attracted the attention of financial analysts, capital market participants and researchers alike. This study is based on share price data on selected companies listed on the New York Stock Exchange as well the market activities of major stock market indexes in the US. The data collated were on monthly basis from January 2000 to February 2017. Trends of these series were plotted and further emphasis highlighted with a descriptive statistics. Share prices and stock market performance trends over the period appear similar. There were perceived signs of stability between January 2000 and 2008:Q2. However, the adverse effects of the 2008 global financial crisis were visible and significant as all the series nosedived, notably between 2008:Q3 and 2009:Q2. From our evidence, relative recovery from the crisis began to be felt from July 2009. Thereafter, the pace of growth in performances across the series has been quite impressive. Both the covariance and principal components analysis results indicate that stock market performance and share prices have direct relationship. The covariance results further showed that the relations so revealed are positive and significant. JEL: C32, F36, G15, E60 Article visualizations:

This study adopts causality in mean and variance approach to investigate dynamic relationship between stock market in an oil‐exporting country (Iran) and the international oil market. The empirical results imply that in view of underlying data‐generating process of the series, the variance of oil price fluctuations does not cause the variance of Iran stock returns. This means that there is no volatility spillover effect between Iran stock market and international oil market.

The nature of stock market movement has always been ambiguous for investors because of various influential factors. This study aims to significantly reduce the risk of trend prediction with machine learning and deep learning algorithms. Four stock market groups, namely diversified financials, petroleum, non-metallic minerals and basic metals from Tehran stock exchange, are chosen for experimental evaluations. This study compares nine machine learning models (Decision Tree, Random Forest, Adaptive Boosting (Adaboost), eXtreme Gradient Boosting (XGBoost), Support Vector Classifier (SVC), Naïve Bayes, K-Nearest Neighbors (KNN), Logistic Regression and Artificial Neural Network (ANN)) and two powerful deep learning methods (Recurrent Neural Network (RNN) and Long short-term memory (LSTM). Ten technical indicators from ten years of historical data are our input values, and two ways are supposed for employing them. Firstly, calculating the indicators by stock trading values as continues data, and secondly converting indicators to binary data before using. Each prediction model is evaluated by three metrics based on the input ways. The evaluation results indicate that for the continues data, RNN and LSTM outperform other prediction models with a considerable difference. Also, results show that in the binary data evaluation, those deep learning methods are the best; however, the difference becomes less because of the noticeable improvement of models’ performance in the second way.

We employ the Markov Regime-Switching GARCH (MRS- GARCH) family models under the normal, Student's t-, and GED distributions to measure the uncertainty of the industry index returns (IIR) of Tehran Stock Exchange over the period of 2013-2019. The models distinguish between two different regimes in both conditional mean and conditional variance. The results show that the MRS-EGARCH-in-mean (MRS-EGARCH-M) models under GED and Student's t-distributions have the best performance to model the IIR volatility. We find evidence of regime-switching behaviour in Iran's stock market. After removing the forecastable component (expected variation) from the best fitted models, we measure the time series of the IIR uncertainty (unforecastable component) and estimate the impact of exchange rate fluctuations on them using an autoregressive distributed lag (ARDL) model. We find that foreign exchange rate fluctuations have a significant and distinct impact on the IIR uncertainty across various regimes. The results show that the exchange rate generally has a negative and positive impact on the IIR uncertainty for export and import-oriented industries, respectively, under both regimes.

During the past few decades, there have been many evidences to believe that the stock markets around the world follow cyclical trends. In this paper, we study the cyclical trends using wavelet function based on various time windows on some major stock market indices. We use two methods of Daubechies and reverse bi-orthogonal wavelet methods and determine the optimal values of both methods. The results are used for Tehran stock exchange using the most recent ten years daily information as an empirical study. The details of our analysis on TEDPIX index for the last decade indicate that there are, at least, four trends of weekly, monthly, quarterly and yearly and the cycles would be expected to be repeated in future.

The purpose of the study had been aimed to further the understanding in exploring the relevance performance of the monopoly stock of Tenaga Nasional Berhad (TNB) to assess the stock performance return in comparison against the Malaysian stock market with reference towards the measurement of the Kuala Lumpur Stock Exchange (KLSE) market index performance as the benchmark. With reference to the previous studies, there is relevance support to identify the tendency of the findings to suggest the higher performance for the major stocks like TNB stock where the business model of TNB being monopolizing the industry creating the upper hand for the stability in driving the revenue and profit leading to higher value in the stock price. The methodology of the research had further the quantitative analysis study using the historical data of 10years from 2014 to 2023 to identify the potential pattern and trend to assess the comparison for the performance and trading trend for both the TNB stock and market index of KLSE. The outcome of the research had suggested the sufficient evidence to identify the higher average return for the TNB stock over the negative return average being achieved by the KLSE market index putting clear picture on the higher performance of the monopoly TNB stock. In addition, the growth of the trading volume trend had suggested that the investors are being higher confidence towards the growth of the TNB stock where the growth of the trading volume for TNB stock is higher than the trading volume for KLSE market index and even exceeding the average return for the TNB stock. This had been in alignment with the previous study where the outcome for the study had created the significant contribution towards the academic and investors to invest in the monopoly stock like TNB and extending the potential area of study for the future research. References Abdullahi, I.B. (2020). ‘Effect of Unstable Macroeconomic Indicators on Banking Sector Stock Price Behaviour in Nigerian Stock Market’, International Journal of Economics and Financial Issues, 10(2), 1-5. Adeyeye, P.O., Aluko, O.A. & Migiro, S.O. (2018). ‘The global financial crisis and stock price behaviour: time evidence from Nigeria’, Global Business and Economics Review, 20(3), 373-387. Al-Awadhi, A.M., Alsaifi, K., Al-Awadhi, A. & Alhammadi, S. (2020). ‘Death and contagious infectious diseases: Impact of the COVID-19 virus on stock market returns’, Journal of Behavioral and Experimental Finance, 27. Alsabban, S. & Alarfaj, O. (2020). ‘An Empirical Analysis of Behavioral Finance in the Saudi Stock Market: Evidence of Overconfidence Behavior’, International Journal of Economics and Financial Issues, 10(1), 73-86. Altig, D., Baker, S., Barrero, J.M., Bloom, N., Bunn, P., Chen, S., Davis, S.J., Leather, J., Meyer, B., Mihaylov, E., Mizen, P., Parker, N., Renault, T., Smietanka, P. & Thwaites, G. (2020). ‘Economic uncertainty before and during the COVID-19 pandemic’, Journal of Public Economics, 191. Apuke, O.D. (2017). ‘Quantitative Research Methods A Synopsis Approach’, Arabian Journal of Business and Management Review (Kuwait Chapter), 6(10). Asif, M., Pasha, M. A., Shafiq, S., & Craine, I. (2022). Economic Impacts of Post COVID-19. Inverge Journal of Social Sciences, 1(1), 56-65. Bhuva, K.K., Mankad, Y.B. & Bhatt, P.B. (2017). ‘Validity of Capital Asset Pricing Model & Stability of Systematic Risk (Beta) of FMCG - A Study on Indian Stock Market’, Journal of Management Research and Analysis, 4(2), 69-73. Chien, M., Lee, C., Hu, T. & Hu, H. (2015). ‘Dynamic Asian stock market convergence: Evidence from dynamic cointegration analysis among China and ASEAN-5’, Economic Modelling, 51, 84-98. Cooper, D. & Schindler, P. (2014). Business Research Methods, 12th edn, McGraw-Hill/Irwin. Boston. Grønholdt, L., Martensen, A., Jørgensen, S. & Jensen, P. (2015). ‘Customer experience management and business performance’, International Journal of Quality and Service Sciences, 7(1), 90-106. He, P., Sun, Y., Zhang, Y. & Li, T. (2020). ‘COVID–19’s Impact on Stock Prices across Different Sectors- an Event Study Based on the Chinese Stock Market’, Emerging Markets Finance and Trade, 56, 2198-2212. Iqbal, H. & Riaz, T. (2015). ‘THE EMPIRICAL RELATIONSHIP BETWEEN STOCKS RETURNS, TRADING VOLUME AND VOLATILITY: EVIDENCE FROM STOCK MARKET OF UNITED KINGDOM’, Research Journal of Finance and Accounting, 6(13), 180-192. Javanmard, H. & Hasani, H. (2017). ‘The Impact of Market Orientation Indices, Marketing Innovation, and Competitive Advantages on the Business Performance in Distributer Enterprises’, The Journal of Industrial Distribution & Business, 8(1), 23-31. Jin, X. (2016). ‘The impact of 2008 financial crisis on the efficiency and contagion of Asian stock markets: A Hurst exponent approach’, Finance Research Letters, 167-175. Lew, C., & Saville, A. (2021). Game-based learning: Teaching principles of economics and investment finance through Monopoly. The International Journal of Management Education, 19(3), 100567. Pasha, M. A., Ramzan, M., & Asif, M. (2019). Impact of Economic Value Added Dynamics on Stock Prices Fact or Fallacy: New Evidence from Nested Panel Analysis. Global Social Sciences Review, 4(3), 135-147. Ruhani, F., Ahmad, T.S.T. & Islam, M.A. (2018). ‘Theories Explaining Stock Price Behavior: A Review of the Literature’, International Journal of Islamic Banking and Finance Research, 2(2), 51-64. Sekaran, U. & Bougie, R. (2016). Research Methods for Business: A Skill-Building Approach, 7th edn, Wiley, New York. Setiawan, C. A., & Rosa, T. (2023). The Analysis of The Effect of Return of Investment (ROI) on Stock Price and Financial Performance of a Company. Journal of Accounting, Management, Economics, and Business (ANALYSIS), 1(1), 20-29. Sharela, B.F. (2016). ‘Qualitative and Quantitative Case Study Research Method on Social Science: Accounting Perspective’, International Journal of Economics and Management Engineering, 10(12), pp. 3849-3854. Sheta, A.F., Ahmed, S.E.M. & Faris, H. (2015). ‘A Comparison between Regression, Artificial Neural Networks and Support Vector Machines for Predicting Stock Market Index’, International Journal of Advanced Research in Artificial Intelligence, 4(7), 55-63. Solares, E., De-León-Gómez, V., Salas, F. G., & Díaz, R. (2022). A comprehensive decision support system for stock investment decisions. Expert Systems with Applications, 210, 118485. Spelta, A., Flori, A., Pecora, N., Buldyrev, S. & Pammolli, F. (2020). ‘A behavioral approach to instability pathways in financial markets’, Nature Communications, 11. Vasileiou, E. (2021). ‘Behavioral finance and market efficiency in the time of the COVID-19 pandemic: does fear drive the market?’, International Review of Applied Economics, 35(2), 224-241. Vergara-Fernández, M., Heilmann, C. & Szymanowska, M. (2023). ‘Describing model relations: The case of the capital asset pricing model (CAPM) family in financial economics’, Studies in History and Philosophy of Science, 97, 91-100. Vinodkumar, N. & AlJasser, H.K. (2020). ‘Financial evaluation of Tadawul All Share Index (TASI) listed stocks using Capital Asset Pricing Model’, Investment Management and Financial Innovations, 17(2), 69-75. Vintila, G., Gherghina, S.C. & Toader, D.A. (2019). ‘Exploring the Determinants of Financial Structure in the Technology Industry: Panel Data Evidence from the New York Stock Exchange Listed Companies’, Journal of Risk Financial Management, 12(4). Wahyuny, T. & Gunarsih, T. (2020). ‘COMPARATIVE ANALYSIS OF ACCURACY BETWEEN CAPITAL ASSET PRICING MODEL (CAPM) AND ARBITRAGE PRICING THEORY (APT) IN PREDICTING STOCK RETURN (CASE STUDY: MANUFACTURING COMPANIES LISTED ON THE INDONESIA STOCK EXCHANGE FOR THE 2015-2018 PERIOD)’, Journal of Applied Economics in Developing Countries, 5(1), 23-30. Wibowo, A. & Darmanto, S. (2020). ‘Empirical Test of the Capital Asset Pricing Model (CAPM): Evidence from Indonesia Capital Market, International Journal of Economics and Management Studies, 7(5), 172-177.

Problem statement: In spite of significant development in Iran stock market as a emerging stock market, there has been not specific research on the causality between the stock prices and economic growth. This study represented a systematic investigation of the relationship between stock market performance and economic growth in Iran by conducting causality tests within the Vector Error Correction Model (VECM) framework. Approach: To achieve this objective unit root tests are fulfilled for all time series data in their levels and their first differences. Johansen co-integration analysis is used to investigate whether the variables are co-integrated of the same order taking into account the maximum eigenvalues and trace statistics tests. A vector error correction model is applied to examine the long-run relationship between stock market performance and economic growth. Finally, Granger causality test is applied in order to find the direction of causality between the examined variables of the estimated model. Results: Findings imply the causality link between economic growth and stock price fluctuations in the long run, as well as bilateral causality running between share prices and economic growth in the short run. Conclusion: Therefore, it can be inferred that the level of real economic activity is the main factor in the movement of stock prices in the long run and stock market plays a role as a leading economic indicator of future economic growth in Iran in the short run.

The impact of oil price shocks on Tehran Stock Exchange returns: Application of the Markov switching vector autoregressive models

Stock market is affected by news and information. If the stock market is not efficient, the reaction of stock price to news and information will place the stock market in overreaction and under-reaction states. Many models have been already presented by using different tools and techniques to forecast the stock market behavior. In this study, the reaction of stock price in the stock market was modeled by the behavioral finance approach. The population of this study included the companies listed on the Tehran Stock Exchange. In order to forecast the stock price, the final price data of the end December, March, June, and September 2006-2015 and the stock prices of 2014 and 2015 were analyzed as the sample. In this study, Bayes' rule was used to estimate the probability of the model change. Through this rule, the probability of an event can be calculated by conditioning the occurrence or lack of occurrence of another event. The results of model estimation showed that there is the probability of being placed in high-fluctuated regimes (overreaction) and low- fluctuated (under-reaction of stock price despite the shocks entered to the stock market. In modelling with the 4-month final prices, it was proved that the real stock price had no difference from the market price.

This study examines the factors influencing the disclosure of information related to the Sustainable Development Goals (SDGs) and its impact on corporate value. Utilizing data from firms listed on the Tehran Stock Exchange (TSE) from 2016 to 2023, this study analyzes the relationships between SDG disclosure and corporate value (TOBINQ) while considering the moderating roles of stakeholder engagement, economic development, and good governance. The research findings indicate that SDG disclosure has a generally positive and significant impact on corporate value. Specifically, the coefficient of 2.203 (p<0.001) for SDG_DISC in the regression models suggests that companies engaging in SDG-related disclosures have been able to attract greater market value. These results align with prior studies on the relationship between corporate social responsibility and firm value. The role of moderating variables has also been examined in this study. Notably, the interaction between SDG disclosure and stakeholder engagement, with a coefficient of 0.159 (p<0.01), indicates that firms actively engaging with their stakeholders can derive greater value from SDG disclosure. Additionally, the interaction between SDG disclosure and good governance, with a coefficient of 2.086 (p<0.001), underscores the importance of effective governance structures in enhancing corporate value. However, the findings also highlight existing challenges in adopting and implementing SDGs at the corporate level, as the SDG disclosure rate among firms remains significantly low (mean = 0.042). This underscores the need for increased awareness and education on the importance of SDG-related disclosures and their benefits for companies and stakeholders. Ultimately, this study recommends that regulatory and governmental bodies play an active role in promoting SDG disclosure by establishing policies and regulations that encourage transparency in this area. Future research can further explore the determinants of SDG disclosure and its implications for firms’ financial and social performance.

The prediction of stock groups values has always been attractive and challenging for shareholders due to its inherent dynamics, non-linearity, and complex nature. This paper concentrates on the future prediction of stock market groups. Four groups named diversified financials, petroleum, non-metallic minerals, and basic metals from Tehran stock exchange were chosen for experimental evaluations. Data were collected for the groups based on 10 years of historical records. The value predictions are created for 1, 2, 5, 10, 15, 20, and 30 days in advance. Various machine learning algorithms were utilized for prediction of future values of stock market groups. We employed decision tree, bagging, random forest, adaptive boosting (Adaboost), gradient boosting, and eXtreme gradient boosting (XGBoost), and artificial neural networks (ANN), recurrent neural network (RNN) and long short-term memory (LSTM). Ten technical indicators were selected as the inputs into each of the prediction models. Finally, the results of the predictions were presented for each technique based on four metrics. Among all algorithms used in this paper, LSTM shows more accurate results with the highest model fitting ability. In addition, for tree-based models, there is often an intense competition between Adaboost, Gradient Boosting, and XGBoost.