Jul 2026· Review of Behavioral Finance· Vol 18, pp. 546-566· 0 citations· 62 references
TL;DR
The results show that both ML and DL models provide strong forecasting performance for the BIST100 Index, and suggest that BIST100 dynamics are shaped by the joint influence of economic fundamentals, market sentiment and liquidity conditions.
Abstract
This study examines the daily closing level of the Borsa Istanbul 100 (BIST100) Index using a unified framework that combines machine-learning (ML) and deep-learning (DL) methods with macro-financial, behavioral and market-based indicators.
The empirical model analyzes a dataset consisting of 3,222 trading days spanning January 2010 to October 2022. The explanatory variable set includes foreign ownership, the policy rates of the Central Bank of the Republic of Türkiye and the US Federal Reserve, the consumer price index, the USD/TRY exchange rate, the Amihud illiquidity measure, and an investor-sentiment index derived from securities investment-trust discounts. Forecasting performance is evaluated within a common model-comparison framework.
The results show that both ML and DL models provide strong forecasting performance for the BIST100 Index. Across specifications, macro-financial variables contain the strongest predictive information, while liquidity and sentiment contribute complementary explanatory content. Overall, the findings suggest that BIST100 dynamics are shaped by the joint influence of economic fundamentals, market sentiment and liquidity conditions. The study contributes to the BIST100 and emerging-market forecasting literature by evaluating these determinants within an integrated data-driven framework.
This study pioneers a unified forecasting framework that simultaneously evaluates macroeconomic fundamentals, market illiquidity and behavioral sentiment, moving beyond the isolated approaches common in the literature. Furthermore, it bridges the gap between high predictive accuracy and economic interpretability, employing rigorous lagged-return validations to capture genuine predictive alpha without look-ahead bias.
Stock market prediction is a significant research topic in the financial sector and has been widely investigated by researchers and investors. Forecasting stock markets is challenging because of the nonlinearity, volatility, and dynamics of the data. Additionally, stock markets are affected by various internal and external factors. While most previous studies relied on historical prices and technical indicators (TIs), they ignored the influence of overall economic factors on stock markets. In contrast, this study introduces a robust framework to predict daily log returns by leveraging a combined dataset comprising historical data, TIs, and macroeconomic data, including gold and oil prices, the volatility index, the dollar index, the interest rate, the 10-year Treasury yield, the term spread, and the dividend yield. Moreover, we propose a hybrid feature selection (FS) approach that combines filter and wrapper methods, unlike in previous studies, which relied primarily on a single FS approach or neglected it entirely. The dataset represents diverse sectors and firm sizes, covering five companies: Apple (AAPL Inc.), Exxon Mobil Corporation (XOM), Goldman Sachs (GS), Pfizer Inc. (PFE), and Ford Motor Company (F). We apply a hybrid evaluation approach that incorporates 5-fold time series cross-validation (TSCV) with a holdout test set to evaluate the efficiency of the proposed models. The results revealed that despite modest improvements in statistical metrics, FS significantly enhanced the economic performance of the trading strategy, as demonstrated by better returns and Sharpe ratios. The results show that deep learning (DL) models that combine macroeconomic data and the FS process, in addition to historical data and TIs, achieved higher trading returns and produced superior risk-adjusted performance, although they demonstrated slightly higher forecast errors than traditional models. This confirms that statistical accuracy alone is insufficient for evaluating financial forecasting models. This work highlights the benefits of the proposed framework for predicting stock returns across different markets, offering significant insights for financial analysts.
Aya Nabil, S. Barakat, Ahmed Aboelfetouh et al.· Scientific Reports· 0 citations
This study forecasts the cash holdings (CASH) of listed companies in Vietnam based on data from 2018-2025 using a machine learning approach. Using panel data with 4,752 observations, the study compares seven algorithms and identifies HistGradientBoosting as the optimal model (R2 approx. 0.7145), far surpassing traditional linear regression (R2 approx. 0.28). This result demonstrates strong non-linearity in liquidity management behavior in the Vietnamese market. Using SHAP and Permutation Importance, the study successfully elucidates the underlying predictive mechanisms. The main drivers are net working capital (NWC) and the current ratio (CR). Notably, short-term debt (STD), interest expense (IE), and the World Uncertainty Index for Vietnam (WUIVN) consistently showed positive effects, strongly reinforcing the Precautionary Motive. The study also found a moderating effect of size, indicating that small businesses are more sensitive and vulnerable to systemic shocks. The application of machine learning models not only improves forecasting accuracy but also provides a transparent view of corporate financial strategies in an uncertain economic environment.
Thu Phuong Nguyen· Tạp chí Khoa học Đại học Côn...· 0 citations
Over the past few years, a multitude of investors have suffered significant financial losses due to erroneous stock market predictions. The inherent difficulty in forecasting market trends establishes the core objective of this research. Investor risk can be mitigated, and predictive accuracy enhanced, if market participants are equipped with comprehensive data regarding the fundamental determinants of equity pricing. Accordingly, this study aims to identify and analyze the critical factors driving stock price fluctuations.
Specifically, this research examines the impact of selected macroeconomic indicators—namely foreign exchange rates, money supply, and foreign exchange reserves—on the Bombay Stock Exchange (BSE) Sensex. The empirical analysis utilizes monthly data sourced from authoritative repositories, spanning the period from April 2021 to March 2026. Following a comprehensive review of existing literature, the dataset was subjected to unit root testing to evaluate its stationarity. Furthermore, the widely accepted Johansen co-integration technique was employed to establish long-term relationships between the dependent and independent variables, while the Granger causality test was applied to assess the direction of causal linkages among these factors.
A. Purohit, Piyush Kumar· Adolescência e Saúde· 0 citations
This study investigates the short and long run impacts of macroeconomic variables inflation, the BI Rate, the USD/IDR exchange rate, and world gold prices on the Indonesian Composite Stock Price Index (IHSG). Utilizing 120 monthly observations from January 2016 to December 2025, this period accounts for severe market turbulences, including the early 2025 trading halts. Given the mixed integration orders I(0) and I(1)), an ARDL bounds testing framework and an Unrestricted Error Correction Model (UECM) with HC3 robust standard errors were applied. The ARDL bounds test reveals no stable long run cointegration (F"-statistic"=2.192, below the lower critical bound), indicating that macroeconomic indicators do not establish a long term equilibrium with the IHSG. Conversely, short run dynamics demonstrate that contemporaneous rupiah depreciation significantly dampens the IHSG. Lagged inflation exhibits a positive effect, while gold prices stimulate the index concurrently but induce a negative effect in the subsequent month, reflecting a delayed safe haven rotation. The BI Rate shows no significant direct impact once exchange rate dynamics are controlled. These findings imply that the IHSG is primarily driven by immediate currency shocks and commodity price pressures rather than long term macroeconomic anchoring.
Siti Syefira Salsabila, Al’an Falina Rizkya, Rizke Maulina et al.· Golden Ratio of Auditing Res...· 0 citations
Predicting financial asset returns remains one of the most difficult challenges in empirical finance, driven by the low signal-to-noise ratio and the semi-strong form of market efficiency. While deep learning models, especially LSTM networks, have shown promise in capturing temporal dependencies, standard architectures often struggle to account for the cross-sectional heterogeneity of asset returns. This paper proposes a novel architectural extension to the basic LSTM model designed to improve both predictive accuracy and model interpretability. The framework integrates macro-financial covariates to capture broader economic signals and learnable sector embeddings to encompass heterogeneity by sector. The trading strategy involves constructing a long-short portfolio based on daily directional forecasts for each S&P 500 constituent, targeting stocks expected to under- or outperform the cross-sectional median return of the S&P 500. Model Performance is evaluated against three competitive benchmarks: a basic LSTM, a Random Forest model and a traditional market buy-and-hold strategy. The empirical results demonstrate that the LSTM with sector embeddings outperforms all benchmarks across key risk and return metrics. By utilizing sector embeddings, the model explicitly incorporates cross-sectional heterogeneity, allowing it to adapt to varying industry dynamics within the market. To address the black-box nature of deep learning, I use latent space visualizations to analyse how the model differentiates between sectors, providing insights into the internal representation of the sectors in the LSTM. The impact of the sector information can be quantified using a novel contribution metric by inspecting the weights of the LSTM. The predictive signal is driven by a short-term reversal factor and an industry momentum factor.
Julius Döbelt· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
