This study builds a quality-minus-junk factor (QMJ) for Chinese A-shares stock via partial least square method. Of the pillars contained in this factor, only the profitability indicators deliver consistent portfolio return, while growth, safety and dividend add little. QMJ retains positive but modest alpha after standard factors, largely overlapping with RMW, and it does help elevate the performance measured with Sharpe ratio of various portfolio. Its distinct value emerges when paired with size. The return of QMJ portfolio shows a convex curvature relation with SMB, generating clear evidence of market timing. Since the existing studies emphasize size factor is the main driving force stirring market in China, investors should consider the combination of quality with size, not using it alone.
A fundamental challenge in quantitative finance and organizational sciences is to quantify the time-lagged relationship between a company's internal organizational dynamics and its tangible outputs. This study introduces an analytical framework that models this relationship using a quantum-inspired holographic concept. Applying a multi-stage statistical pipeline to 10 years of public data from six firms, we tested time-series models representing innovation and collaboration. The analysis revealed this new framework functions as an effective analytical filter for out-of-sample data. The results indicate that per-company calibrated models—which synchronize objective output data with calibrated, conceptually paired proxy metrics (like R&D spend for innovation)—achieved statistically significant predictive power (p = 0.021) against financial productivity data, whereas traditional, single-variable models did not. The findings demonstrate this Holographic Evaluation System for Topologic Interrelational Analysis (HESTIA) framework is a robust method for developing and validating firm-specific models for profits and valuation. The process is analogous to an imaging technique, transforming noisy proxy signals from a latent signal domain into an interpretable map of a firm's unique operational rhythm. The resulting models visualize a firm's value-creation cycle with a statistically high likelihood of predicting future “productivity,” which in this study is defined as profit and share price.
The volatility of gold prices significantly influences global financial stability, necessitating the development of reliable models capable of producing precise forecasts to minimize investment risks and maximize profitability. Recently, both machine learning and deep learning approaches have gained significant traction for time series forecasting across scientific and industrial domains. In this paper, we propose the ForCNN model, which utilizes grayscale image-based input rather than traditional numerical data. This algorithm integrates the advantages of visual image representation of a time series and deep 2D convolution neural network to analyze and extract important features and generate accurate forecasts. We carried out extensive experiments on two real-world gold closing price datasets and showed ForCNN outperformed most of the state-of-the-art deep learning techniques such as MLP, CNN1D, LSTM, CNN-LSTM, BiLSTM, CNN-BiLSTM in terms of accuracy measures. Furthermore, portfolio performance evaluation using Cumulative Return, Average Daily Return, and Sharpe Ratio indicates that ForCNN achieves superior profitability and stronger risk-adjusted performance, thereby underscoring its effectiveness in practical financial forecasting applications.
We establish that the actions of influential opinion leaders in the digital currency markets and potential investors following their lead drive abnormal cryptocurrency returns. We develop a psychological and behavioral factor, named the herd behavior index, that detects the herd instinct of the investors in cryptocurrency markets and captures anomalies in cryptocurrency returns. Our finding shows that the herd behavior index can explain the variation in cryptocurrency returns. Moreover, there exists a timeseries relationship between abnormal returns and the investors’ herd instinct, and the herd behavior index consistently forecasts future digital currency returns. Finally, we find notable gains even after considering transaction costs by implementing a long/short trading strategy based on the herd behavior index.
In technical analysis-based algorithmic trading strategies, we use historical price patterns to predict future prices and trade accordingly. This is analogous to machine learning where we use the existing data patterns to classify or predict new patterns. This paper uses this analogy and explains trading strategies as a machine learning classification problem. We derive simple approximations that relate the performance of trading strategies to machine learning statistics. We introduce a new performance measure of the Return Efficiency Index. This index provides a link between trading strategy return statistics and classification accuracy. It has a simple geometric interpretation, similar to the ROC index in machine learning, and can be used to compare strategies in terms of their ability to capture the potential returns possible with the underlying assets. We illustrate the proposed approach by a detailed comparison of daily trading strategies designed by analogies to nearest neighbor classification widely used in machine learning and to some strategies based on deep learning.
In this paper, a shorter and more publication focused version of our recent article "A Bottom-Up Approach to the financial Markets" ( Mahdavi-Damghani, & Roberts, S. 2019.) is presented. More specifically we propose a new approach to studying the financial markets using the Bottom-Up approach instead of the traditional Top-Down. We achieve this shift in perspective, by re-introducing the High Frequency Trading Ecosystem (HFTE) model Mahdavi-Damghani, B. 2017. More specifically we specify an approach in which agents in Neural Network format designed to address the complexity demands of most common financial strategies interact through an Order-Book. We introduce in that context concepts such as the Path of Interaction in order to study our Ecosystem of strategies through time. We show how a Particle Filter methodology can then be used in order to track the market ecosystem through time. Finally, we take this opportunity to explore how to build a realistic market simulator which objective would be to test real market impact without incurring any research costs.
This paper presents an approach to index portfolio re-balancing, focusing on the median slice of asset performance instead of the more traditional focus on “winners” and “losers.” In the proposed approach, one constructs an equal-weight portfolio from the index’s median (by returns) component. We consider the Dow Jones Industrial Average (DJIA) as a case study and introduce a systematic re-balancing strategy that targets the middle third (“median”) segment of asset performers within the index. The proposed methodology provides significantly better returns and mitigates drawdowns compared with a passive “buy-and-hold” strategy while promoting a disciplined and simple portfolio re-balancing strategy. The study empirically evaluates the effectiveness of the median-based re-balancing strategy over historical data. We compare our strategy to a benchmark portfolio closely tracking the DJIA index and other popular re-balancing strategies focusing on winners and losers, including the Dogs of the Dow strategy. We provide a simple model to compare factor loadings offered by such strategies and show that the median strategy provides broad diversification across sectors. We also analyze factor exposures of the proposed strategy using the 3-factor Fama-French model. The analysis demonstrates that the “median” rotation strategy consistently outperforms the Dow Jones and the broad market index S&P-500, yielding higher returns and reduced drawdowns.
This paper contributes to the existing stock market anomaly literature by being the first to analyze the benefits of combining two distinct anomalies; specifically, the low-volatility and mean-reversion anomalies. Our results show that on a long-only basis, these two time-varying anomalies could be combined into a double-sort investment strategy that includes some desirable characteristics from each of them, thereby making the portfolio return accumulation more stable over time. As the added-value of low-volatility investing stems mostly from the risk-reduction side, while contrarian stocks are generally highly volatile with remarkable upside potential, the use of the double-sort portfolio-formation in which the contrarian stocks are picked from the sub-set of below-median volatility stocks can shorten the below-market performance periods that have occasionally materialized for plain low-volatility or plain contrarian investors.
We obtain the bond price formula for the fractional Cox-Ingersoll-Ross model. Then we obtain option price formula for the bond. Finally we apply it to derive option price formula in fractional Heston model.
We present an algorithmic trading strategy based upon a graph version of the dynamic mode decomposition (DMD) model. Unlike the traditional DMD model which tries to characterize a stock’s dynamics based on all other stocks in a universe, the proposed model characterizes a stock’s dynamics based only on stocks that are deemed relevant to the stock in question. The relevance between each pair of stocks in a universe is represented as a directed graph and is updated dynamically. The incorporation of a graph model into DMD effects a model reduction that avoids overfitting of data and improves the quality of the trend predictions. We show that, in a practical setting, the precision and recall rate of the proposed model are significantly better than the traditional DMD and the benchmarks. The proposed model yields portfolios that have more stable returns in most of the universes we backtested.
Smart Beta Investing has revolutionized investment management field with the ability to offer higher returns with lower costs. The momentum factor in the Smart Beta universe often outperforms other popular factors, besides being well documented in the literature, it is found to be pervasive across different geographies and asset classes. In this paper, we implement a long-only momentum based investment strategy for the Indian equity markets that delivers superior risk-adjusted performance, derived upon comparing multiple strategies across time frames. Based on these tests, we find that the lagged 6-months' compounded returns indicator with quarterly rebalancing can be used to generate the highest risk-adjusted performance.The paper also tests a related phenomenon called the Accelerated Effect of momentum as documented by Ardila et. al. (2021) for the Indian equity market, and finds that the accelerated momentum effect underperforms the traditional momentum both on an absolute and risk-adjusted basis.
This article uses Principal Component Analysis to compute and extract the main factors for the financial risk of a portfolio, to determine the most dominating stock for each risk factor and for each portfolio and finally to compute the total risk of the portfolio. Firstly, each dataset is standardized and yields a new datasets. For each obtained dataset a covariance matrix is constructed from which the eigenvalues and eigenvectors are computed. The eigenvectors are linearly independent one to another and span a real vector space where the dimension is equal to the number of the original variables. They are also orthogonal and yield the principal risk components (pcs) also called principal risk axis, principal risk directions or main risk factors for the risk of the portfolios. They capture the maximum variance (risk) of the original dataset. Their number may even be reduced with minimum (negligible) loss of information and they constitute the new system of coordinates. Every principal component is a linear combination of the original variables (stock rate of returns). For each dataset, each financial transaction can be written as a linear combination of the eigenvectors. Since they are mutually orthogonal and linearly independent and that they capture the maximum variance of the original data, the risk of the portfolio is calculated by using the principal components, then they have been used to calculate the total risk of the portfolio which is a weighted sum of the variance explained by the principal components.
In this paper, a shorter and more publication focused version of our recent article “A Bottom-Up Approach to the financial Markets” (Mahdavi-Damghani, & Roberts, S. 2019.) is presented. More specifically we propose a new approach to studying the financial markets using the Bottom-Up approach instead of the traditional Top-Down. We achieve this shift in perspective, by re-introducing the High Frequency Trading Ecosystem (HFTE) model Mahdavi-Damghani, B. 2017. More specifically we specify an approach in which agents in Neural Network format designed to address the complexity demands of most common financial strategies interact through an Order-Book. We introduce in that context concepts such as the Path of Interaction in order to study our Ecosystem of strategies through time. We show how a Particle Filter methodology can then be used in order to track the market ecosystem through time. Finally, we take this opportunity to explore how to build a realistic market simulator which objective would be to test real market impact without incurring any research costs.
Using an index fund is a popular strategy that is designed to simulate the behavior of a market index and obtain the excess return that is more stable than other mutual funds. In setting up an index fund, investors must first choose a small number of stocks and then assign a weight to each selected stock. However, with traditional methods, investors hardly determine how well the designed index fund can mimic the market index. The main objective of this paper is to demonstrate the improvement of index fund performance by using a multi-objective optimization algorithm that can assign weights automatically.
Index tracking is one of the most popular passive strategy in portfolio management. However, due to some practical constrains, a full replication is difficult to obtain. Many mathematical models have failed to generate good results for partial replicated portfolios, but in the last years a data driven approach began to take shape. This paper proposes three heuristic methods for both selection and allocation of the most informative stocks in an index tracking problem, respectively XGBoost, Random Forest and LASSO with stability selection. Among those, latest deep autoencoders have also been tested. All selected algorithms have outperformed the benchmarks in terms of tracking error. The empirical study has been conducted on one of the biggest financial indices in terms of number of components in three different countries, respectively Russell 1000 for the USA, FTSE 350 for the UK, and Nikkei 225 for Japan.
This paper aims at computing optimal control policies to drive a self-financing portfolio of financial assets from a given initial financial state to a final state in a given time horizon such that for the first case, the functional portfolio financial risk is minimized and, for the second case, the functional portfolio profit is maximized The optimal control policies are the optimal investment allocation processes, the optimal state process is the optimal investor's wealth process, also called the system response to the input control and is obtained by solving the combined system of differential equations formed by the state and costate system of differential equations derived and extracted from Pontryagin's Minimum Principle. Computational simulations are provided to show the effectiveness and the reliability of the approach.
We examine the effect of VIX futures' new trading hours on price discovery as these causal relations have not been investigated before and are consequential for regulators and practitioners involved in the VIX futures market. Our data include VIX futures and VIX ETPs for four different periods in which trading hours were changed. Employing three different measures of information share, we find that VXX ETN leads VIX futures in 2009 and 2010, while in 2011 and 2013, the ETPs' leadership varies depending on the exchange-traded product under consideration. Furthermore, in 2013 before the change of trading hours, the VIX futures contribute more to price discovery than they do after trading hours expansion. Less of the price discovery occurs from the exchange-traded products in the latter half of the trading period in 2010. OLS regression results of the determinants of price discovery as well as panel regression results show that the effect of volume and spread, which are the main determinants of price discovery in the prior literature, change significantly before and after futures trading hour expansions, for both VIX futures and ETPs.
