Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Heni Boubaker has a total of 14 co-authors. Here are the top co-authors by number of shared publications:

  • Amal Ladhari

    Research Laboratory of Economics, Management and Quantitative Finance (LaREMFiQ), Economics and Quantitative Methods Department, Institute of Higher Commercial Studies of Sousse, University of Sousse, Sousse 4054, Tunisia

    1 shared publication
  • Ameni Ben Hadj Abdallah

    Economics, Management and Quantitative Finance Research Laboratory (LaREMFiQ), Institute of High Commercial Studies of Sousse, University of Sousse, Sousse 4054, Tunisia

    1 shared publication
  • Amina Ladhari

    Economics, Management, and Quantitative Finance Research Laboratory (LaREMFiQ), Institute of High Commercial Studies of Sousse, Economics and Quantitative Methods Department, University of Sousse, Sousse 4054, Tunisia

    1 shared publication
  • Amina Ladhari

    Economics, Management, and Quantitative Finance Research Laboratory (LaREMFiQ), Institute of High Commercial Studies of Sousse, Economics and Quantitative Methods Department, University of Sousse, Sousse 4054, Tunisia

    1 shared publication
  • Bouthaina Ben Othman

    Economics, Management and Quantitative Finance Research Laboratory (LaREMFiQ), Institute of High Commercial Studies of Sousse, University of Sousse, Sousse 4054, Tunisia

    1 shared publication
  • Gadir Alomair

    Department of Quantitative Methods, School Business, King Faisal University, Al-Ahsa 31982, Saudi Arabia

    1 shared publication

Latest Publications

  • Open Access

    Conditional Integration of AI Equities with Traditional and Alternative Assets: Evidence from Wavelet Coherence and Time-Varying Connectedness

    by Heni Boubaker, Nadia Farjallah

    This study examines whether the equities of leading artificial intelligence (AI) firms were integrated with Bitcoin, gold, West Texas Intermediate (WTI) crude oil and clean energy from January 2018 to July 2026. Using an equally weighted index of NVIDIA, Apple, Alphabet and Microsoft, we combine wavelet coherence, time-varying parameter vector autoregressive (TVP-VAR) connectedness and time-varying Granger causality, complemented by windowed scalogram difference and variance decomposition analyses. Dependence is time-varying and horizon-dependent: significant co-movements concentrate around the COVID-19 crash, the 2022 inflation and monetary tightening shock, and the AI-driven boom. Average total connectedness was low (20.23%) but exceeded 50% in March 2020. Clean energy and the AI index are net transmitters of shocks, whereas Bitcoin, gold and oil are net receivers; however, much of the transmitting role of AI equities reflects their exposure to the broad equity market. Lagged predictability is episodic, and AI equities are almost never predicted by the other assets. The results are robust to ex ante AI exchange-traded funds, alternative model specifications, weekly data and Brent oil. AI equities therefore appear only conditionally integrated with other asset classes, and diversification benefits observed in calm periods should not be assumed to persist during stress episodes.

  • Open Access

    Beyond Cash Flows: Valuing Solar Energy Under Material Risk and Technological Learning

    by Amal Ladhari, Heni Boubaker

    Conventional project finance values renewable assets as a deterministic stream of discounted cash flows, treating capital cost as fixed and the underlying engineering as a black box. This paper examines how far such static NPV analysis can misprice utility-scale solar PV when two dynamics are ignored: the decline of capital cost driven by technological learning, and the volatility transmitted from critical-material markets (polysilicon and silver) into CAPEX. Using a monthly calibration dataset of 78 observations (January 2020–June 2026), we compare three nested valuation models for a representative 100 MW plant: a deterministic DCF/NPV baseline (Model A), a Monte Carlo stochastic DCF (Model B), and a real-options model that values the flexibility to defer while learning lowers future CAPEX (Model C). With CAPEX decomposed so that the silver already embedded in module prices is not counted twice, Model A reports a static NPV of +US$5.9 million and an unconditional “invest” signal. Model B has the same mean but reveals a 37.7% probability of loss and a 5% conditional value-at-risk (CVaR, expected shortfall) of US$21.4 million. A variance decomposition attributes 99% of this dispersion to electricity-price risk; material prices explain less than 1% of NPV variance in the global baseline and about 9% in a contracted German setting. Material markets matter instead through the level of CAPEX and through the estimation of learning: conditioning the experience curve on polysilicon prices lowers the apparent learning rate in price levels from about 40% to 28% (first-difference estimates are too imprecise to confirm the gap formally), and feeding the naive rate into Model C would almost double the option premium. With project volatility (22%) and the expected CAPEX decline (3.0%) both calibrated from the data, Model C values the opportunity at US$9.8 million and favors deferral unless CAPEX is expected to rise by more than about 9% within the year. A Tunisia–Germany comparison, with expected exchange rate movements treated consistently across models, shows that the cost of capital and currency risk dominate cross-country differences in value and risk.

  • Open Access

    SupTech and Greenwashing in European Banking: A Causal and Nonlinear Heterogeneous Analysis Using Synthetic Control and Causal Random Forest

    by Mejda Tebessi, Heni Boubaker

    This paper examines whether the adoption of Supervisory Technology (SupTech) is associated with a reduction in greenwashing in the European banking sector over the period 2014–2025. Using a progressive empirical framework combining the Synthetic Control Method (SCM), a split-sample SCM, an OLS regression of the SCM-estimated treatment effect, and a Causal Random Forest (CRL) via T-Learner applied to a panel of European banks, we provide evidence consistent with a meaningful reduction in greenwashing associated with SupTech adoption, which is robust across multiple identification and validation strategies. The split-sample SCM and OLS analyses reveal that this effect is amplified by higher capital adequacy, genuine ESG engagement, and stricter regulatory environments, while larger banks exhibit a systematically attenuated response. Contrary to the complementarity hypothesis, RegTech does not reinforce SupTech’s disciplining effect; instead, the evidence points to a substitution mechanism whereby banks with developed internal compliance infrastructure derive limited marginal benefit from external supervisory technology. The Causal Random Forest analysis provides evidence of a statistically significant and stable average treatment effect and indicates that bank digital maturity and FinTech adoption are the most consistent drivers of SupTech’s effectiveness. Policy simulations show that improving digital maturity, rather than RegTech endowment, yields the largest additional greenwashing-reduction gains. These findings suggest that SupTech acts as a credibilization mechanism whose effectiveness depends on the stringency of the external regulatory architecture and the digital absorptive capacity of supervised institutions. External validity to less harmonized regulatory environments remains an open empirical question.

  • Open Access

    Environmental Constraints in Cryptocurrency Portfolio Optimization: A Mean-CVaR Analysis

    by Sawssen Araichi, Ons Belhedi, Heni Boubaker, Gadir Alomair

    Sustainable investing raises an important question: do environmental restrictions affect the risk–return characteristics of cryptocurrency portfolios? This study compares Mean-CVaR optimal portfolios across Green, Dirty, and Mixed cryptocurrency universes using daily returns for 12 cryptocurrencies from January 2022 to September 2025. Ethereum (ETH) was classified as Dirty before its transition from Proof-of-Work to Proof-of-Stake in September 2022 and as Green thereafter. Each universe is optimized independently using the Non-Dominated Sorting Genetic Algorithm II (NSGA-II), Strength Pareto Evolutionary Algorithm 2 (SPEA2), and Particle Swarm Optimization (PSO), with CVaR measured at the 95% confidence level. The results show that, in the Post-Merge period, the Green universe exhibits a higher CVaR than the Dirty and Mixed universes under all three algorithms. This result remains consistent across the main robustness analyses and is confirmed by an exact optimization benchmark. The asset-exclusion analysis further shows that excluding Bitcoin (BTC) increases CVaR under all three algorithms, whereas excluding ETH does not produce the same effect. These findings indicate that environmental screening can alter portfolio risk by changing the assets available for investment. For sustainability-oriented investors, the financial effect of such restrictions therefore depends on the assets excluded from the portfolio.

  • Open Access

    Carbon Pricing Uncertainty and the Green Finance Ecosystem: Connectedness, Contagion, and Portfolio Strategies

    by Bouthaina Ben Othman, Rihab Bedoui Ben Salem, Heni Boubaker

    Carbon price instability within the EU Emissions Trading System (EU ETS) is associated with financial stress that propagates across green finance markets, yet the system-level dynamics linking carbon allowance instruments, clean energy equities, green bonds, and oil volatility remain insufficiently characterized over the turbulent 2021–2026 period. This paper applies the DCC-GARCH R2 decomposed connectedness framework to five exchange-traded funds and one volatility index spanning the principal channels through which EU ETS regulatory shocks propagate to financial markets, and derives a novel Connectedness-Based Hierarchy Index (CBHI) that translates the transmitter–receiver hierarchy into a time-varying portfolio desirability index. Five key findings emerge. First, the carbon allowance futures ETF (KRBN) and the Paris-aligned equity ETF (CARB) form a near-closed systemic bloc within this asset universe: bilateral connectedness reaches 0.867, with to and from directional connectedness values both approaching 80%. Second, this co-transmitter structure is highly contingent on the joint inclusion of both instruments; excluding CARB raises KRBN’s CBHI from 0.251 to 22.204, reclassifying it as a structural diversifier and reducing the mean Total Connectedness Index (TCI) from 52.18% to 30.81%. Third, system-wide connectedness averages 52.18% but surges to nearly 73% during EU ETS regulatory crises. Fourth, connectedness-aware portfolios outperform the minimum-variance benchmark across all risk-adjusted metrics, yielding an annualized Sharpe ratio of 0.148 vs. −1.066 (T=1035 observations, daily rebalancing, zero transaction costs); this improvement is driven by reallocation toward crude oil volatility (OVX), the sole non-ETF and most peripheral instrument (to = 5.55%, CBHI=14.310), which the CBHI identifies as the system’s dominant structural diversifier and whose weight rises from 0.4% in the benchmark to 31.6%. Fifth, the CBHI uncovers a structural tension in Paris-aligned mandates: CARB records the second-lowest CBHI (0.254), indicating that climate alignment and systemic risk minimization are partially conflicting objectives.


  • Open Access

    Improving Ethereum Price Forecasting Through Hybrid Decomposition and LSTM–Attention Mechanisms

    by Amina Ladhari, Heni Boubaker

    This study investigates the predictive performance of decomposition-based deep learning models through a focused case study on Ethereum price forecasting. Using hourly Ethereum price data from 5 September 2020 to 13 July 2025, we develop hybrid forecasting frameworks that integrate three signal decomposition techniques—Wavelet Decomposition (WD), Variational Mode Decomposition (VMD), and Empirical Mode Decomposition (EMD)—with a Long Short-Term Memory network enhanced by an attention mechanism (LSTM–Attention). The decomposition methods are first applied to extract multiple frequency components from the original time series, allowing the forecasting model to capture both short-term fluctuations and long-term dynamics inherent in this specific digital asset. Each decomposed component is then modeled using the LSTM–Attention architecture, and the forecasts are aggregated to produce the final prediction. The predictive performance of the proposed models is evaluated using MAE, MSE, RMSE, and MAPE, and the results are compared with benchmark models including ARIMA-GARCH and standard LSTM–Attention. Forecast accuracy is assessed through out-of-sample one-step-ahead predictions, and robustness is ensured by averaging results across 10 independent runs. The empirical results demonstrate that incorporating decomposition techniques substantially improves forecasting accuracy. Among the tested models, the EMD–LSTM–Attention framework achieves the best performance, producing the lowest forecasting errors. While focused on the Ethereum market, these findings highlight the effectiveness of combining signal decomposition and attention-based deep learning architectures to enhance predictive performance in high-volatility cryptocurrency environments.


  • Top Cited Papers
    Open Access

    A Hybrid HAR-LSTM-GARCH Model for Forecasting Volatility in Energy Markets

    by Wiem Ben Romdhane, Heni Boubaker

    Accurate volatility forecasting in energy markets is paramount for risk management, derivative pricing, and strategic policy planning. Traditional econometric models like the Heterogeneous Auto-regressive (HAR) model effectively capture the long-memory and multi-component nature of volatility but often fail to account for non-linearities and complex, unseen dependencies. Deep learning models, particularly Long Short-Term Memory (LSTM) networks, excel at capturing these non-linear patterns but can be data-hungry and prone to overfitting, especially in noisy financial datasets. This paper proposes a novel hybrid model, HAR-LSTM-GARCH, which synergistically combines the strengths of the HAR model, an LSTM network, and a GARCH model to forecast the realized volatility of crude oil futures. The HAR component captures the persistent, multi-scale volatility dynamics, the LSTM network learns the non-linear residual patterns, and the GARCH component models the time-varying volatility of the residuals themselves. Using high-frequency data on Brent Crude futures, we compute daily Realized Volatility (RV). Our empirical results demonstrate that the proposed HAR-LSTM-GARCH model significantly outperforms the benchmark HAR, GARCH(1,1), and standalone LSTM models in both statistical accuracy and economic significance, offering a robust framework for volatility forecasting in the complex energy sector.


  • Open Access

    Enhancing Predictive Performance of LSTM–Attention Models for Investment Risk Forecasting

    by Amina Ladhari, Heni Boubaker

    For many decades, time-series forecasting has been applied to different problems by scientists and industries. Many models have been introduced for the purpose of forecasting. These advancements have significantly improved the accuracy and reliability of predictions, especially in complex scenarios where traditional methods struggled. As data availability continues to expand, the integration of machine learning techniques is likely to further enhance forecasting capabilities across various fields. Today, hybrid techniques are gaining popularity, as they combine the advantages of different approaches to deliver improved predictive performance and more advanced visualization analytics for decision support. These hybrid approaches can provide better prediction, and at the same time, they can develop a more sophisticated set of visualization analytics for decision support. Recently, the integration of cross-entropy, fuzzy logic, and attention mechanisms in hybrid forecasting models has enhanced their ability to capture complex and uncertain patterns in financial and energy markets. In this study, we propose a hybrid ANN–LSTM deep learning model optimized with cross-entropy, fuzzy logic, and an attention mechanism to enhance the forecasting of financial and energy time series, specifically Ethereum and natural gas prices. Our models combine the feature extraction strength of ANN with the temporal learning of LSTM, while cross-entropy improves convergence, fuzzy logic handles uncertainty, and attention refines feature weighting. Since inaccurate forecasts can lead to greater estimation uncertainty and increased financial and operational risk, improving predictive reliability is essential for effective risk mitigation. These techniques prove effective not only in improving estimation accuracy but also in minimizing financial risks and supporting more informed investment decisions.


  • Open Access

    Wavelet Estimation for Density and Copula Functions

    by Heni Boubaker, Houcem Belgacem

    This article investigates the problem of univariate and bivariate density estimation using wavelet decomposition techniques. Special attention is given to the estimation of copula functions, which capture the dependence structure between random variables independent of their marginals. We consider two distinct frameworks: the case of independent and identically distributed (i.i.d.) variables and the case where variables are dependent, allowing us to highlight the impact of the dependence structure on the performance of wavelet-based estimators. Building on this framework, we propose a novel iterative thresholding method applied to the detail coefficients of the wavelet transform. This iterative scheme aims to enhance noise reduction while preserving significant structural features of the underlying density or copula function. Numerical experiments illustrate the effectiveness of the proposed method in both univariate and bivariate settings, particularly in capturing localized features and discontinuities in the presence of varying dependence patterns.

  • Open Access

    Metaheuristics for Portfolio Optimization: Application of NSGAII, SPEA2, and PSO Algorithms

    by Ameni Ben Hadj Abdallah, Rihab Bedoui, Heni Boubaker

    This work looks for the optimal allocation of different assets, namely, the G7 stock indices, commodities (gold and WTI crude oil), cryptocurrencies (Bitcoin and Ripple), and S&P Green Bond, over four periods: before the COVID-19 crisis, during the COVID-19 crisis and before the Russia–Ukraine war, during the COVID-19 crisis and Russia–Ukraine war, and after the COVID-19 pandemic and during the Russia–Ukraine war. Metaheuristics, Non-dominated Sorting Genetic Algorithm (NSGAII), Strength Pareto Evolutionary Algorithm (SPEA2), and Particle Swarm Optimization (PSO) are applied to find the best allocation. The results reveal that there a significant preference for the S&P Green Bond during the four periods of study according to three algorithms, thanks to its portfolio diversification abilities. During the COVID-19 pandemic and the geopolitical crisis, the most optimal portfolio was Nikkei 225 because of its quick recovery from the pandemic and poor reliance on the Russia–Ukraine markets, while WTI crude oil and both dirty and clean cryptocurrencies were poor contributors to the investment portfolio because these assets are sensitive to geopolitical problems. After the end of the pandemic and during the ongoing Russia–Ukraine war, the three algorithms obtained remarkably different results: the NSGAII portfolio was invested in various assets, 32% of the SPEA2 portfolio was allocated to the S&P Green Bond, and half of the PSO portfolio was allocated to the S&P Green Bond too. This may be due to changes in investors’ preferences to protect their fortune and to diversify their portfolio during the war. From a risk-averse perspective, NSGAII does not underestimate the risk, while in terms of forecasting accuracy, PSO is an adequate algorithm. In terms of time, NSGAII is the fastest algorithm, while SPEA2 requires more time than the NSGAII and PSO algorithms. Our results have important implications for both investors and risk managers in terms of portfolio and risk management decisions, and they highlight the factors that influence investment choices during health and geopolitical crises.