Avishay Aiche
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Avishay Aiche has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Gil Cohen
Management Department, Western Galilee College, Acre 2412101, Israel
5 shared publications - Ron Eichel
Western Galilee College
2 shared publications - Zvi Winer
Department of Management, Western Galilee Academic College, Akko, Israel
2 shared publications - Amit Gayer
Economics and Management Department, Tel-Hai College, Qiryat Shemona 9977, Israel
1 shared publication - Aner Sela
Department of Economics, Ben-Gurion University of the Negev, Beer Sheva, Israel
1 shared publication Benyamin Shitovitz
University of Haifa, Israel
1 shared publication
Latest Publications
- Open Access
- 22 October 2026
- Published by MDPI AG in Urban Science
- Vol. 10 (11) , 612
Investigating the Links Between Air Pollution, Arnona Property Taxation and Housing Prices: A Hedonic Analysis of the Haifa Housing Market
Air pollution imposes measurable economic costs on housing markets, typically reflected in lower property values. While this negative capitalization is well documented, the interaction between environmental externalities and active municipal fiscal policy has received less empirical attention within the context of non-ad valorem systems, presenting a distinct area of study in urban economics. This study addresses this gap by examining the relationship between municipal taxation, air pollution, and housing prices in Haifa, Israel—a city operating under a distinctive, area-based property tax system (“Arnona”). Unlike ad valorem systems where tax liabilities adjust automatically to market shifts, the Arnona system requires administrative intervention to modify tax zones, providing a unique setting to observe deliberate policy responses. Using a dataset of 5108 housing transactions (2020–2025) and a two-stage least squares (2SLS) instrumental variable approach, we demonstrate that air pollution is a robust predictor of municipal tax rates. Our results reveal a “compensatory fiscal mechanism”: neighborhoods with higher industrial pollutants (SO2 and NOX) face significantly lower tax rates. Conversely, PM10 displays a positive association with tax rates, likely reflecting a centrality premium linked to urban density. We conclude that while municipal tax adjustments partially compensate residents for environmental burdens, they do not fully offset the market penalty associated with pollution exposure.
- 22 October 2026
- Published by MDPI AG in Urban Science
- Vol. 10 (11) , 612
Open AccessInvestigating the Links Between Air Pollution, Arnona Property Taxation and Housing Prices: A Hedonic Analysis of the Haifa Housing Market
Air pollution imposes measurable economic costs on housing markets, typically reflected in lower property values. While this negative capitalization is well documented, the interaction between environmental externalities and active municipal fiscal policy has received less empirical attention within the context of non-ad valorem systems, presenting a distinct area of study in urban economics. This study addresses this gap by examining the relationship between municipal taxation, air pollution, and housing prices in Haifa, Israel—a city operating under a distinctive, area-based property tax system (“Arnona”). Unlike ad valorem systems where tax liabilities adjust automatically to market shifts, the Arnona system requires administrative intervention to modify tax zones, providing a unique setting to observe deliberate policy responses. Using a dataset of 5108 housing transactions (2020–2025) and a two-stage least squares (2SLS) instrumental variable approach, we demonstrate that air pollution is a robust predictor of municipal tax rates. Our results reveal a “compensatory fiscal mechanism”: neighborhoods with higher industrial pollutants (SO2 and NOX) face significantly lower tax rates. Conversely, PM10 displays a positive association with tax rates, likely reflecting a centrality premium linked to urban density. We conclude that while municipal tax adjustments partially compensate residents for environmental burdens, they do not fully offset the market penalty associated with pollution exposure.
- Open Access
Entropy-Augmented Forecasting and Portfolio Construction at the Industry-Group Level: A Causal Machine-Learning Approach Using Gradient-Boosted Decision Trees
This paper examines whether information-theoretic complexity measures enhance industry-group return forecasting and portfolio construction within a machine-learning framework. Using daily data for 25 U.S. GICS industry groups spanning more than three decades, we augment gradient-boosted decision tree models with Shannon entropy and fuzzy entropy computed from recent return dynamics. Models are estimated at weekly, monthly, and quarterly horizons using a strictly causal rolling-window design and translated into two economically interpretable allocation rules, a maximum-profit strategy and a minimum-risk strategy. Results show that the top performing strategy, the weekly maximum-profit model augmented with Shannon entropy, achieves an accumulated return exceeding 30,000%, substantially outperforming both the baseline model and the fuzzy-entropy variant. On monthly and quarterly horizons, entropy and fuzzy entropy generate smaller but robust improvements by maintaining lower volatility and better downside protection. Industry allocations display stable and economically interpretable patterns, profit-oriented strategies concentrate primarily in cyclical and growth-sensitive industries such as semiconductors, automobiles, technology hardware, banks, and energy, while minimum-risk strategies consistently favor defensive industries including utilities, food, beverage and tobacco, real estate, and consumer staples. Overall, the results demonstrate that entropy-based complexity measures improve both economic performance and interpretability, yielding industry-rotation strategies that are simultaneously more profitable, more stable, and more transparent.
Open AccessEntropy-Augmented Forecasting and Portfolio Construction at the Industry-Group Level: A Causal Machine-Learning Approach Using Gradient-Boosted Decision Trees
This paper examines whether information-theoretic complexity measures enhance industry-group return forecasting and portfolio construction within a machine-learning framework. Using daily data for 25 U.S. GICS industry groups spanning more than three decades, we augment gradient-boosted decision tree models with Shannon entropy and fuzzy entropy computed from recent return dynamics. Models are estimated at weekly, monthly, and quarterly horizons using a strictly causal rolling-window design and translated into two economically interpretable allocation rules, a maximum-profit strategy and a minimum-risk strategy. Results show that the top performing strategy, the weekly maximum-profit model augmented with Shannon entropy, achieves an accumulated return exceeding 30,000%, substantially outperforming both the baseline model and the fuzzy-entropy variant. On monthly and quarterly horizons, entropy and fuzzy entropy generate smaller but robust improvements by maintaining lower volatility and better downside protection. Industry allocations display stable and economically interpretable patterns, profit-oriented strategies concentrate primarily in cyclical and growth-sensitive industries such as semiconductors, automobiles, technology hardware, banks, and energy, while minimum-risk strategies consistently favor defensive industries including utilities, food, beverage and tobacco, real estate, and consumer staples. Overall, the results demonstrate that entropy-based complexity measures improve both economic performance and interpretability, yielding industry-rotation strategies that are simultaneously more profitable, more stable, and more transparent.
- Open Access
Artificial Intelligence Models for Predicting Stock Returns Using Fundamental, Technical, and Entropy-Based Strategies: A Semantic-Augmented Hybrid Approach
This study examines the effectiveness of combining semantic intelligence drawn from large language models (LLMs) such as ChatGPT-4o with traditional machine-learning (ML) algorithms to develop predictive portfolio strategies for NASDAQ-100 stocks over the 2020–2025 period. Three different predictive frameworks––fundamental, technical, and entropy-based––are tested through examination of novel combinations of ML- and LLM-derived semantic metrics. The empirical results reveal a considerable divergence in optimal blending methods across the methodologies; namely, the technical methodology exhibits the best performance when using only ML predictions, with around 1978% cumulative returns with monthly rebalancing. In contrast, the fundamental methodology achieves its full potential when it is based primarily on LLM-derived semantic insights. The Entropy methodology is improved by a balanced combination of both semantic and ML signals, thus highlighting the potential of LLMs to improve predictive power by offering interpretative context for complex market interactions. These findings highlight the strategic importance of tailoring the semantic–algorithmic fusion to suit the nature of the predictive data and the investment horizon, with significant implications for portfolio management and future research in financial modeling.
Open AccessArtificial Intelligence Models for Predicting Stock Returns Using Fundamental, Technical, and Entropy-Based Strategies: A Semantic-Augmented Hybrid Approach
This study examines the effectiveness of combining semantic intelligence drawn from large language models (LLMs) such as ChatGPT-4o with traditional machine-learning (ML) algorithms to develop predictive portfolio strategies for NASDAQ-100 stocks over the 2020–2025 period. Three different predictive frameworks––fundamental, technical, and entropy-based––are tested through examination of novel combinations of ML- and LLM-derived semantic metrics. The empirical results reveal a considerable divergence in optimal blending methods across the methodologies; namely, the technical methodology exhibits the best performance when using only ML predictions, with around 1978% cumulative returns with monthly rebalancing. In contrast, the fundamental methodology achieves its full potential when it is based primarily on LLM-derived semantic insights. The Entropy methodology is improved by a balanced combination of both semantic and ML signals, thus highlighting the potential of LLMs to improve predictive power by offering interpretative context for complex market interactions. These findings highlight the strategic importance of tailoring the semantic–algorithmic fusion to suit the nature of the predictive data and the investment horizon, with significant implications for portfolio management and future research in financial modeling.
- 9 May 2025
- Published by Emerald Publishing in China Finance Review International
- Vol. ahead-of-p (ahead-of-p)
Matching angels to startups using AI
Purpose: This paper introduces an innovative approach to analyzing the matching process between angel investors and start-up companies, utilizing a combination of artificial intelligence (AI) technologies and game-theoretic models. By harnessing the capabilities of AI engines such as Gemini and ChatGPT 4, we extract valuable insights from real-world data, identifying influential criteria that drive investment decisions on both sides of the equation.Design/methodology/approach: Leveraging historical investment patterns and behaviors, Gemini identifies key criteria that angel investors prioritize when evaluating start-up opportunities. We then employ R programming simulation to evaluate the predictive quality of these criteria and optimize cutoff values using the Youden index, balancing sensitivity and specificity in the matching process.Findings: Our findings underscore the importance of integrating qualitative preferences and quantitative criteria in the matching process, offering a comprehensive framework for guiding strategic investment decisions in the entrepreneurial ecosystem. By comparing and contrasting the results obtained from different methodologies, we gain valuable insights into the complexities and dynamics of the investment landscape, paving the way for informed decision-making and strategic partnerships. Our research contributes to advancing the field of angel investing, offering practical insights and tools to support investors, entrepreneurs and stakeholders in navigating the dynamic and evolving landscape of early-stage investment.Originality/value: This is the first attempt to utilize AI in the matching process between startups and angel investors.
- 9 May 2025
- Published by Emerald Publishing in China Finance Review International
- Vol. ahead-of-p (ahead-of-p)
Matching angels to startups using AI
Purpose: This paper introduces an innovative approach to analyzing the matching process between angel investors and start-up companies, utilizing a combination of artificial intelligence (AI) technologies and game-theoretic models. By harnessing the capabilities of AI engines such as Gemini and ChatGPT 4, we extract valuable insights from real-world data, identifying influential criteria that drive investment decisions on both sides of the equation.Design/methodology/approach: Leveraging historical investment patterns and behaviors, Gemini identifies key criteria that angel investors prioritize when evaluating start-up opportunities. We then employ R programming simulation to evaluate the predictive quality of these criteria and optimize cutoff values using the Youden index, balancing sensitivity and specificity in the matching process.Findings: Our findings underscore the importance of integrating qualitative preferences and quantitative criteria in the matching process, offering a comprehensive framework for guiding strategic investment decisions in the entrepreneurial ecosystem. By comparing and contrasting the results obtained from different methodologies, we gain valuable insights into the complexities and dynamics of the investment landscape, paving the way for informed decision-making and strategic partnerships. Our research contributes to advancing the field of angel investing, offering practical insights and tools to support investors, entrepreneurs and stakeholders in navigating the dynamic and evolving landscape of early-stage investment.Originality/value: This is the first attempt to utilize AI in the matching process between startups and angel investors.
- 19 November 2024
- Published by Elsevier in Finance Research Letters
- Vol. 71
Intelligent forecasting in bitcoin markets
- 19 November 2024
- Published by Elsevier in Finance Research Letters
- Vol. 71
Intelligent forecasting in bitcoin markets
- Open Access
- 19 November 2024
- Published by MDPI AG in Forecasting
- Vol. 6 (4) , 1065-1077
Constructing Cybersecurity Stocks Portfolio Using AI
This study explores the application of artificial intelligence, specifically ChatGPT-4o, in constructing and managing a portfolio of cybersecurity stocks over the period from Q1 2018 to Q1 2024. Leveraging advanced machine learning models, fundamental analysis, sentiment analysis, and optimization techniques, the AI-driven portfolio significantly outperformed leading cybersecurity ETFs, as well as broader market indices such as the Nasdaq 100 (QQQ) and S&P 500 (SPY). The methodology employed included data collection, stock filtering, predictive modeling using Random Forests and Support Vector Machines (SVMs), sentiment analysis through natural language processing (NLP), and portfolio optimization using Mean-Variance Optimization (MVO), with quarterly rebalancing to ensure responsiveness to evolving market conditions. The AI-selected portfolio achieved a total return of 273%, with strong risk-adjusted performance as demonstrated by key metrics such as the Sharpe ratio, highlighting the effectiveness of an AI-based approach in navigating market complexities and generating superior returns. The results of this study indicate that AI-driven portfolio management can uncover investment opportunities that traditional methods may overlook, offering a competitive edge in the cybersecurity sector and promising enhanced predictive accuracy, efficiency, and overall investment success as AI technologies continue to evolve.
- 19 November 2024
- Published by MDPI AG in Forecasting
- Vol. 6 (4) , 1065-1077
Open AccessConstructing Cybersecurity Stocks Portfolio Using AI
This study explores the application of artificial intelligence, specifically ChatGPT-4o, in constructing and managing a portfolio of cybersecurity stocks over the period from Q1 2018 to Q1 2024. Leveraging advanced machine learning models, fundamental analysis, sentiment analysis, and optimization techniques, the AI-driven portfolio significantly outperformed leading cybersecurity ETFs, as well as broader market indices such as the Nasdaq 100 (QQQ) and S&P 500 (SPY). The methodology employed included data collection, stock filtering, predictive modeling using Random Forests and Support Vector Machines (SVMs), sentiment analysis through natural language processing (NLP), and portfolio optimization using Mean-Variance Optimization (MVO), with quarterly rebalancing to ensure responsiveness to evolving market conditions. The AI-selected portfolio achieved a total return of 273%, with strong risk-adjusted performance as demonstrated by key metrics such as the Sharpe ratio, highlighting the effectiveness of an AI-based approach in navigating market complexities and generating superior returns. The results of this study indicate that AI-driven portfolio management can uncover investment opportunities that traditional methods may overlook, offering a competitive edge in the cybersecurity sector and promising enhanced predictive accuracy, efficiency, and overall investment success as AI technologies continue to evolve.
- 5 January 2021
- Published by Springer Nature in Electronic Commerce Research
- Vol. 22 (4) , 1351-1375
Online sequential bundling: profit analysis and practice
We investigate monopoly profit under a new online tying strategy, namely sequential bundling. This method allows customers to buy additional products at discounted prices immediately after purchasing one or some of the available products. This strategy has been practiced by Walmart and others but has not been modelled to date. We use microeconomics analysis to conduct a comparison of the gained profit with the three commonly used bundling strategies: no bundling, pure bundling and mixed bundling. The main result shows that the sequential bundling strategy yields higher profits in comparison to all three classic strategies. In particular, for the symmetric cost case, our model provides a useful tool for practitioners such as common online shops.
- 5 January 2021
- Published by Springer Nature in Electronic Commerce Research
- Vol. 22 (4) , 1351-1375
Online sequential bundling: profit analysis and practice
We investigate monopoly profit under a new online tying strategy, namely sequential bundling. This method allows customers to buy additional products at discounted prices immediately after purchasing one or some of the available products. This strategy has been practiced by Walmart and others but has not been modelled to date. We use microeconomics analysis to conduct a comparison of the gained profit with the three commonly used bundling strategies: no bundling, pure bundling and mixed bundling. The main result shows that the sequential bundling strategy yields higher profits in comparison to all three classic strategies. In particular, for the symmetric cost case, our model provides a useful tool for practitioners such as common online shops.
- 11 May 2019
- Published by Elsevier in Economics Letters
- Vol. 181, 107-110
The asymptotic kernel in TU production market games with symmetric big players and a uniform ocean of small players
- 11 May 2019
- Published by Elsevier in Economics Letters
- Vol. 181, 107-110
The asymptotic kernel in TU production market games with symmetric big players and a uniform ocean of small players
- Open Access
- 1 November 2018
- Published by Elsevier in Economics Letters
- Vol. 172, 34-36
Tullock contests reward information advantages
- 1 November 2018
- Published by Elsevier in Economics Letters
- Vol. 172, 34-36
Open AccessTullock contests reward information advantages
- 12 June 2018
- Published by Springer Nature in International Journal of Game Theory
- Vol. 48 (2) , 411-421
On the equal treatment imputations subset in the bargaining set for smooth vector-measure games with a mixed measure space of players
- 12 June 2018
- Published by Springer Nature in International Journal of Game Theory
- Vol. 48 (2) , 411-421
On the equal treatment imputations subset in the bargaining set for smooth vector-measure games with a mixed measure space of players