Multi-factor Model Research Articles

Quantitative Factor Exploration Based on Insider Trading Detection

Factor research has always been the focus of financial quantitative forecasting research. In the existing multi-factor strategies, we have noticed that the combination modes of factors are different and arbitrary. We hope to develop a more accurate and effective multi-factor model by selecting the most common and most interpretable multi-factors and combining them with equal weight method and assigned weights developed by Hidden Markov Model after some optimizations applied to selected multi-factors. At the same time, we noticed that in the existing data information, there are reports or information that reveal the insider trading of related companies. The existing reports show that the abnormal data volume caused by insider trading will make the prediction of the model inaccurate. Therefore, we added insider trading as a factor into our model training through the order imbalance algorithm to obtain more accurate prediction results. The results show that the multi-factor model is interpretable and effective, and its effect is better than the predicted value than that of the single factor model. After adding the related factors of insider trading into the forecast, it has a certain normalization effect on the original predicted value with large deviation, but has little influence on the effect of the original value with small deviation, which proves the effectiveness of our factor based on insider trading.

Financial Market Reactions under the Russia-Ukraine Conflict-An Empirical Study Based on a Multi-factor Model

This paper takes advantage of the turbulent situation in eastern Ukraine to study and examine the correlation between war conflicts and stock yields, and to study the impact on the stock returns of A-share listed companies in China. The background of this article is that with the Russian Ministry of Defense announcing the withdrawal of troops stationed on the border between Russia and Ukraine, the crisis situation in eastern Ukraine has been cooling since October 2021, until February 2022, when Ukraine announced in civilian forces that it would evacuate the local population to Russia on the same day, while the situation in eastern Ukraine deteriorated, the local government banned foreign aircraft from entering the country, and declared Ukraine a state of war. This article constructs an index factor that measures the degree of war through the cryptocurrency market price fluctuation index and the cryptocurrency market price fluctuation index. In addition, a new war impact index factor is added to the basic three-factor model, and the explanatory performance of the new multi-factor model for the stock yield of listed companies is more in-depth and whether it is more explanatory than the three-factor model. The study will test whether the Russian-Ukrainian conflict will significantly affect equity returns in China's A-share market. Helps investors better describe the expected returns of a cross-sectional stock portfolio.

Supply chain partnership and innovation performance of manufacturing firms: Mediating effect of knowledge sharing and moderating effect of knowledge distance

Affected by complicated issues, such as regional conflicts, trade wars, and the COVID-19 pandemic, manufacturing firms face enormous challenges in reconstructing the global supply chain landscape to form new cooperative innovation mechanisms. This study investigates the relationship between supply chain partnerships (SCP) and innovation performance (IP) from a knowledge-management perspective. A multi-factor conceptual model of this relationship was proposed, considering the mediating effect of knowledge sharing (KS) and the moderating effect of knowledge distance (KD). SCP is measured in three dimensions: trust relationship (TR), commitment relationship (CMR), and contractual relationship (CTR). IP is measured in two aspects: technological innovation performance and management innovation performance. An empirical study was conducted to test the hypotheses using data from 417 valid questionnaires. Confirmatory factor analysis and structural equation modeling were applied to test the hypotheses. The results demonstrate that (1) KS plays a significant mediating role in how SCP impacts IP and that the indirect effect of TR through KS on IP is greater than that of CTR or CMR. (2) KD between supply chain partners plays a significant negative moderating role between KS and IP; that is, the smaller the KD, the higher the IP achievable through sufficient KS. These findings shed new light on building collaborative innovation mechanisms for supply chain management.

Modeling Drinking Milk Consumption Preferences under Climate Change and the Covid-19 Pandemics Conditions

Climate changes and Covid-19 pandemic have dramatically led to adverse impacts on not only the food supply chains but also consumers’ consumption preferences and purchase decisions in the last decade, and thus they have gradually threatened the welfare of current and next generations. The aim of the research was to determine the factors affecting consumers’ milk consumption preference and purchase decisions at TRA1 region in Turkey, and then to construct the first and second-order consumption preference models based on the factors, and finally to test validation of the models. For the purposes, the main data of the study consisted of primary data obtained from 765 households residing in TRA1 region. The data were firstly used in Exploratory Factor Analysis (EFA) to determine factor dimensions, and then in Confirmatory Factor Analysis (CFA) for first and second-order multi-factor measurement models. The results of the study indicated that convergent and discriminant validities for each factor dimension in the CFA model were accepted by according to the compare and goodness-of-fit test threshold criteria. On the other hand, the results also highlighted that hygiene, sensory quality, and reliability factors at a higher level, and brand image, concern and nutrition value factors at a moderate level and milk supply source factor at a minimum level were major indicators on consumers’ milk consumption preferences and purchase decisions. All the factors out of concern factor covering the variables related to climate change and Covid-19 pandemic were of positive relationships on their milk consumption pattern, indeed, but concern factor created the negative impacts on the others. Consequently, contraction of animal-based milk diet consumption could be relatively contributed to mitigate the effects of climate change by being transited gradually to moderate-mixed plant-based milk sources, and then to preparation of new national diet programs related to milk consumption.

Prognostic and immune correlation analysis of mitochondrial autophagy and aging-related genes in lung adenocarcinoma.

Mitophagy and aging (MiAg) are very important pathophysiological mechanisms contributing to tumorigenesis. MiAg-related genes have prognostic value in lung adenocarcinoma (LUAD). However, prognostic, and immune correlation studies of MiAg-related genes in LUAD are lacking. MiAg differentially expressed genes (DEGs) in LUAD were obtained from public sequencing datasets. A prognostic model including MiAg DEGs was constructed according to patients divided into low- and high-risk groups. Gene Ontology, gene set enrichment analysis, gene set variation analysis, CIBERSORT immune infiltration analysis, and clinical characteristic correlation analyses were performed for functional annotation and correlation of MiAgs with prognosis in patients with LUAD. Seven MiAg DEGsof LUAD were identified: CAV1, DSG2, DSP, MYH11, NME1, PAICS, PLOD2, and the expression levels of these genes were significantly correlated (P < 0.05). TheRiskScoreof theMiAgDEGprognostic modeldemonstrated high predictive ability of overall survival of patients diagnosed with LUAD. Patients with high and low MiAg phenotypic scores exhibitedsignificant differences in the infiltration levels of eight types of immune cells (P < 0.05). The multi-factor DEG regression model showed higher efficacy in predicting 5-year survival than 3- and 1-year survival of patients with LUAD. Seven MiAg-related genes were identified to be significantly associated with the prognosis of patients diagnosed with LUAD. Moreover, the identified MiAg DEGs might affect the immunotherapy strategy of patients with LUAD.

Diversification measures: Mutual fund family case

This study introduces a portfolio theory motivated approach to measuring mutual fund family-level risk diversification. The average cross-fund correlation in idiosyncratic returns measures diversification of idiosyncratic risk, while the correlation of predicted returns from the multifactor model measures factor risk diversification within a fund family. We document a substantial cross-sectional variation in family-level diversification measured with our new proxies independent of the number of funds and objectives in the family. While number of objectives is a popular yet possibly misleading measure of diversification, there is a link between portfolio theory-based diversification measures and the number of objectives in a family. On average, fund families with more investment objectives are more diversified in terms of both idiosyncratic and factor risks; yet, in large families, more investment objectives are associated with increased diversification of idiosyncratic risk but decreased diversification of factor risk. Fund family diversification improves family performance during market downturns and in large families. However, fund family diversification does not significantly affect absolute or relative family size, except for the number of investment objectives, which has a negative relation to family size.

Hyperspectral Estimation of SPAD Value of Cotton Leaves under Verticillium Wilt Stress Based on GWO–ELM

Rapid and non-destructive estimation of the chlorophyll content in cotton leaves is of great significance for the real-time monitoring of cotton growth under verticillium wilt (VW) stress. The spectral reflectance of healthy and VW cotton leaves was determined using hyperspectral technology, and the original spectra were processed using Savitzky–Golay (SG) smoothing, and on its basis through mean centering, standard normal variate (SG-SNV), multiplicative scatter correction (SG-MSC), reciprocal second-order differentiation, and logarithmic second-order differentiation ([lg(SG)]″) preprocessing operations. The characteristic bands were selected based on the correlation coefficient, vegetation index, successive projection algorithm (SPA), and competitive adaptive reweighted sampling (CARS). The single-factor model, back propagation neural network of particle swarm optimization algorithm, and extreme learning machine (ELM) of a grey wolf optimizer (GWO) algorithm were constructed to compare and explore the ability of each model to estimate the soil plant analysis development (SPAD) value of cotton under VW stress. The results showed that spectral pretreatment could improve the correlation between characteristic bands and SPAD values. SG-MSC and SG-SNV showed better changes in the five pretreatments, and the maximum correlation coefficients of healthy and VW cotton leaves were higher than 0.74. Compared with SPA, the accuracy of model estimation based on CARS-extracted characteristic bands was higher, and the estimation accuracy of the multi-factor model was better than that of the single-factor model under each pretreatment. For healthy cotton leaves, [lg(SG)]″–CARS–GWO–ELM was the optimal model, with a modeling and validation set R2 of 0.956 and 0.887, respectively. For VW cotton leaves, SG-MSC–CARS–GWO–ELM was the optimal model, with a modeling and validation set R2 of 0.832 and 0.824, respectively. Therefore, the GWO–ELM model constructed under different pretreatments combined with characteristic extraction methods can be used for the estimation of leaf SPAD values under VW stress to dynamically monitor VW stress in cotton and provide a theoretical reference for precision agriculture.

Choosing between value and growth in mutual fund investing

&#x0D; &#x0D; &#x0D; This article informs investors on the choice between value and growth mutual funds. The well- established value premium demonstrates that, on average, value securities outperform growth secu- rities, suggesting that an investor may be wise to choose value funds. Extant studies, however, suggest that growth funds outperform value funds. We show that value funds indeed outperform growth funds especially in terms of lower realized risk and higher realized terminal wealth, leading us to recom- mend value funds over growth funds. We argue that previous findings result from a bias against value in some multifactor models.&#x0D; &#x0D; &#x0D;

Construction of a Risk Prediction Model for Lung Cancer Based on Lifestyle Behaviors in the UK Biobank Large-Scale Population Cohort

To identify the risk factors related to lifestyle behaviors that affect the incidence of lung cancer, to build a lung cancer risk prediction model to identify, in the population, individuals who are at high risk, and to facilitate the early detection of lung cancer. The data used in the study were obtained from the UK Biobank, a database that contains information collected from 502 389 participants between March 2006 and October 2010. Based on domestic and international guidelines for lung cancer screening and high-quality research literature on lung cancer risk factors, high-risk population identification criteria were determined. Univariate Cox regression was performed to screen for risk factors of lung cancer and a multifactor lung cancer risk prediction model was constructed using Cox proportional hazards regression. Based on the comparison of Akaike information criterion and Schoenfeld residual test results, the optimal fitted model assuming proportional hazards was selected. The multiple factor Cox proportional hazards regression was performed to consider the survival time and the population was randomly divided into a training set and a validation set by a ratio of 7:3. The model was built using the training set and the performance of the model was internally validated using the validation set. The area under the receiver operating characteristic (ROC) curve ( AUC) was used to evaluate the efficacy of the model. The population was categorized into low-risk, moderate-risk, and high-risk groups based on the probability of occurrence of 0% to <25%, 25% to <75%, and 75% to 100%. The respective proportions of affected individuals in each risk group were calculated. The study eventually covered 453 558 individuals, and out of the cumulative follow-up of 5 505 402 person-years, a total of 2 330 cases of lung cancer were diagnosed. Cox proportional hazards regression was performed to identify 10 independent variables as predictors of lung cancer, including age, body mass index (BMI), education, income, physical activity, smoking status, alcohol consumption frequency, fresh fruit intake, family history of cancer, and tobacco exposure, and a model was established accordingly. Internal validation results showed that 8 independent variables (all the 10 independent variables screened out except for BMI and fresh fruit intake) were significant influencing factors of lung cancer ( P<0.05). The AUC of the training set for predicting lung cancer occurrence at one year, five years, and ten years were 0.825, 0.785, and 0.777, respectively. The AUC of the validation set for predicting lung cancer occurrence at one year, five years, and ten years were 0.857, 0.782, and 0.765, respectively. 68.38% of the individuals who might develop lung cancer in the future could be identified by screening the high-risk population. We established, in this study, a model for predicting lung cancer risks associated with lifestyle behaviors of a large population. Showing good performance in discriminatory ability, the model can be used as a tool for developing standardized screening strategies for lung cancer.

Volatility Prediton based on Multiple-factor Model

Generally, due to unpredictable and vulnerable features of the stock market, traditional statistical methods with single factor cannot explain the movements of stock prices well. In this paper, multi-factor model of quantitative stock selection is applied to predict stock price index to perceive the fluctuation of stock in multiple aspects and improve the accuracy of prediction. This study also combines machine learning measurements with historical data fitting effects. The data used for analysis is all collected from Tushare website, and the stock data are from the 2015 to 2022 data of Shanghai Pudong Development Bank and China Merchants Bank, and the selected factors include price-to-earnings ratio, price-to-book ratio, volume ratio, total equity and so forth. Ordinary least square linear regression and random forest nonlinear approaches are utilized to predict the stock price. According to the analysis, the accuracy of random forest is higher than OLS in stock price prediction. Among all the factors, the opening price, the highest price and the lowest price have relatively large impacts on the closing price of the next day. However, when selecting different factors, stocks and train-testing periods, the obtained regression models are different. Therefore, the determination of the correlation coefficient is not invariable and needs to be analyzed on a case-by-case basis. Overall, these results shed light on the superiority of machine learning model and the significant contribution of some factors on stock price prediction.

Priced risk in corporate bonds

Recent studies document strong empirical support for multifactor models that aim to explain the cross-sectional variation in corporate bond expected excess returns. We revisit these findings and provide evidence that common factor pricing in corporate bonds is exceedingly difficult to establish. Based on portfolio- and bond-level analyses, we demonstrate that previously proposed bond risk factors, with traded liquidity as the only marginal exception, do not have any incremental explanatory power over the corporate bond market factor. Consequently, this implies that the bond CAPM is not dominated by either traded- or nontraded-factor models in pairwise and multiple model comparison tests.

Study on Rock-Electric Characteristics of Cracked Porous Rocks by the Novel Multifactor Conductivity Model.

Due to the influence of multiple factors on the conductive properties of rocks, the Archie's formula, considering only a single factor, makes it difficult to reasonably explain rock-electric characteristics of cracked porous rocks. In order to better describe the conductive mechanism of cracked porous rocks, a generalized multifactor conductivity model was proposed by considering and introducing multiple influencing factors such as the series-parallel structure, conductive matrix, cracks, and fluids, which is conducive to more accurate research on the conductive mechanism of rocks. It should be noted that the developed model is not only applicable to cracked porous rocks but also useful for porous rocks. Through the study and analysis of various influencing factors, it is demonstrated by the simulation results that both the conductive matrix and cracks improve the conductive ability, which are crucial factors resulting in the non-Archie behavior and low-resistivity pay zone, and rock conductivity is more sensitive to the conductive matrix and cracks in tight reservoirs with porosity below 10%. Furthermore, experimental data are available to validate the novel multifactor conductivity model, and the comparison results show its advantages in predicting and explaining the conductive properties of cracked porous rocks.

An Analytical Model Coupled with Orthogonal Experimental Design Is Used to Analyze the Main Controlling Factors of Multi-Layer Commingled Gas Reservoirs

The majority of China’s multi-layer low permeability tight gas reservoirs are currently being extracted through the method of multi-layer co-production. However, due to the significant disparity in physical properties and varying degrees of pressure depletion among the production layers, elucidating the primary factors influencing the productivity contribution of each gas layer remains challenging. A multi-factor analytical model is proposed for commingled gas wells with multiple layers. An unstable model is established for the production of commingled layers, and the problem of flow distribution is addressed using the Duhamel convolution principle. The Laplace transform is subsequently employed to derive the solution in the Laplace domain, which can be inverted utilizing the Stehfest inversion algorithm to obtain a real-time domain solution. The influence of reservoir factors on the stratification contribution rate has been comprehensively analyzed, encompassing permeability, porosity, initial pressure, drainage radius, and layer thickness. The orthogonal test design was employed to conduct range analysis and variance analysis separately, yielding the primary and secondary order as well as influence weight of the five factors. The findings demonstrate that, within this gas reservoir, the discharge radius, thickness, and porosity are identified as the primary factors influencing gas well productivity. Furthermore, seven horizontal flow charts illustrating the double-layer gas reservoir and five horizontal flow charts depicting single-factor variations in the double-layer gas reservoir were constructed. These charts provide a clear visualization of the impact of each reservoir factor on stratification’s contribution rate. In contrast to previous studies, this novel approach presents a comprehensive optimization framework that ranks the influence weights of individual factors and identifies the most significant factors impacting multi-layer gas reservoirs. The presented method also serves as a foundation for the subsequent selection of multi-layer gas reservoirs, formulation of gas well stimulation measures, and efficient development.

LGBT CEOs and stock returns: Diagnosing rainbow ceilings and cliffs

This study is the first to investigate the implications of lesbian, gay, bisexual, and transgender chief executive officers (LGBT CEOs) for stock performance, using an exhaustive sample of 26 LGBT publicly listed company CEOs since 2000. Firms with openly LGBT CEOs generate a statistically and economically significant monthly alpha of 0.69%− 1.08%, robust to portfolio weighting schemes, estimation frequency, multi-factor asset-pricing models, multicollinearity, sectoral allocation effects, and in subsamples in the United States and globally. The results imply that a “rainbow ceiling” exists with regards to LGBT executives, and that companies they lead are persistently undervalued due to discrimination by investors. LGBT CEOs on average represent small growth stocks with poor past performance, supporting the “rainbow cliff” hypothesis that the LGBT community is overrepresented in precarious leadership positions. Portfolios formed of stocks with LGBT CEOs robustly outperform broad market indices, evidencing attractiveness for ethical investment from both selfish and social perspectives.

Research on the Applicability of Value Investment in China’s A-Share Market

Value investment has been widely respected and applied in the capital market of developed countries, and its effectiveness has also been verified in a large number of practices. However, since it was introduced to China in 1990s, the concept of value investment has been buried for a long time due to the lack of supervision and the backwardness of investment concepts. With the improvement of the market environment, the progress of supervision system and the update of investors’ ideas in recent years, does China’s A-share market have the conditions for value investment? This paper will discuss this problem theoretically and empirically. Firstly, this paper combs the development of value investment theory and expounds the views and propositions of value investment. Secondly, under the guidance of value investment theory, this paper selects the data of CASMR database 2018-2021. In the first stage, five sectors are selected as the low growth and high growth track of value investment by using multi-factor model. In the second stage, using EVA analysis, five leading stocks in each industry are selected for empirical test, combined with the fundamental analysis in each stage. The results show that the average annual rate of return of the top enterprises is over 50% and the average annual rate of return is over 30% in the high-growth industries screened out under the concept of value investment; This paper verifies that value investment is not only suitable for China A-share market, but also an excellent investment idea with low risk and high return, and puts forward some relevant investment suggestions.

How does ESG explain excess returns in emerging market? An Asset-Pricing Approach

Objective: Previous studies found several important risk factors for the capital market in explaining stock performance. However, most studies only consider conventional investment factors without considering sustainable ones. This study examines Environmental, Social, and Governance (ESG) performance’s effect as a risk factor in a multi-factor model. Design/Methods/Approach: This study employs secondary data from the company’s financial reports, annual reports, and Thomson Reuters ESG score data. The sample for this study were companies listed on the LQ45 index during the 2015-2019 period, which were selected using the purposive sampling method and produced a selection of 19 non-financial companies that met the criteria. Findings: The results show that ESG negatively affects 21 out of 30 portfolios, and the four-factor ESG model is better at explaining excess returns than the three-factor Fama-French model. Originality/Value: This study provides new insights by including ESG as a risk factor in the three-factor Fama-French model in explaining stock returns. The existence of the ESG variable allows us to identify whether sustainability is an essential determinant in explaining the average portfolio return. This study adds new insights, where using sustainability reports in the form of ESG can capture cross-sectional variations in stock returns, not only on market factors, size factors, and book-to-market factors. Practical/Policy implication: Given the established evidence that ESG factors can mitigate risk, investors are encouraged to thoroughly evaluate a company’s sustainability report to assess the efficacy of its ESG performance. For managers of companies, this serves as the foundation for developing strategies that will enhance the long-term profitability and sustainability of the organization.

Spatiotemporal wind power forecasting approach based on multi-factor extraction method and an indirect strategy

Accurate ultra-short-term wind power forecasting is a prerequisite for decision making related to the management of power systems. Existing approaches used to forecast wind power ignored the correlation between wind power outputs under similar wind power, which provides important information for wind power forecasting. A spatiotemporal approach based on an indirect strategy and a multi-factor extraction model is proposed in this study to achieve more accurate power prediction. Specifically, wind power and other variables are classified into four categories according to wind direction, and multivariate feature extraction and wind power forecasting are performed separately for each category. In the experimental study, taking two real-world datasets of wind farms in Northeast China as examples, the proposed approach is compared with eight benchmarking approaches, and the results demonstrate the effectiveness and robustness of our approach. In addition, we further conduct the DM test, and the sensitivity analysis to discuss the effect of hyperparameters on forecasting performance. The results of DM verify the superiority of the proposed approach in statistic. This study provides a new high-precision approach and a new forecasting strategy for future wind power forecasting.

Hub gene associated with prognosis in bladder cancer is a novel therapeutic target.

Bladder cancer is a clinical and social conundrum due to its high incidence and recurrence rate. It is urgent to find new targets for the diagnosis and treatment of bladder cancer and improve the prognosis and survival rate of bladder cancer patients. We sought a prognosis-related gene, built related models of evaluated bladder cancer and identified the function of the hub gene in bladder cancer. We downloaded the data of bladder cancer patients from the TCGA database, and used differentially expressed genes (DEGs), copy number variation (CNV) and survival analysis to scan the hub genes associated with prognosis in bladder cancer. Then, multi-factor cox regression was used to obtain the bladder cancer prognosis correlation model. Then, we analyzed the relationship between the expression of hub gene and immune microenvironment of bladder cancer. The relationship between the expression of hub gene and prognosis in bladder cancer patients was verified by immunohistochemistry. Cell proliferation assay and drug sensitivity test in vivo were used to verify the inhibition of bladder cancer by targeted inhibitors. In bladder cancer, we screened seven hub genes (ACLY, CNP, NKIRAS2, P3H4, PDIA6, VPS25 and XPO1) associated with survival. Moreover, the multifactor regression model constructed with hub gene can well distinguish the prognosis of bladder cancer. Hub gene is mostly associated with immune microenvironment. Immunohistochemical results basically confirmed the importance of XPO1 in bladder cancer. Selinexor (an inhibitor of XPO1) could effectively inhibit the proliferation of bladder cancer in the cell proliferation experiments by CCK-8 assays and it could suppress the growth of bladder cancer in mouse bladder cancer model. In this study, a prognostic model with seven hub genes has provided great help for the prognosis prediction of bladder cancer patients. And XPO1 is an important target affecting the prognosis of bladder cancer, and inhibition of XPO1 can effectively inhibit bladder cancer proliferation and growth.

A Study of Multifactor Quantitative Stock-Selection Strategies Incorporating Knockoff and Elastic Net-Logistic Regression

In the data-driven era, the mining of financial asset information and the selection of appropriate assets are crucial for stable returns and risk control. Multifactor quantitative models are a common method for stock selection in financial assets, so it is important to select the optimal set of factors. Elastic Net, which combines the benefits of the L1 and L2 penalty terms, performs better at filtering features due to the complexity of the features in high-dimensional datasets than Lasso and Ridge regression. At the same time, the false discovery rate (FDR), which is important for making reliable investment decisions, is not taken into account by the current factor-selection methodologies. Therefore, this paper constructs the Knockoff Logistic regression Elastic Net (KF-LR-Elastic Net): combining Logistic regression with Elastic Net and using Knockoff to control the FDR of variable selection to achieve factor selection. Based on the selected factors, stock returns are predicted under Logistic regression. The overall model is denoted as Knockoff Logistic regression Elastic Net-Logistic regression (KL-LREN-LR). The empirical study is conducted with data on the CSI 300 index constituents in the Chinese market from 2016–2022. KF-LREN-LR is used for factor selection and stock-return forecasting to select the top 10 stocks and establish an investment strategy for daily position changing. According to empirical evidence, KF-LR-Elastic Net can select useful factors and control the FDR, which is helpful for increasing the accuracy of factor selection. The KF-LREN-LR forecast portfolio has the advantages of high return and controlled risk, so it is informative for optimizing asset allocation.

THE LOW-VOLATILITY ANOMALY AND THE ADAPTIVE MULTI-FACTOR MODEL

The paper provides a new explanation of the low-volatility anomaly. We use the Adaptive Multi-Factor (AMF) model estimated by the Groupwise Interpretable Basis Selection (GIBS) algorithm to find those basis assets significantly related to low and high volatility portfolios. These two portfolios load on very different basis assets, indicating that volatility is not an independent risk, but that it is related to existing risk factors. The out-performance of the low-volatility portfolio is due to the (equilibrium) performance of these loaded risk factors, specifically, the better long-term performance of the asset classes bonds and real estate as contrasted with materials, precious metals, and the healthcare industry. Our methodology is applicable to any long–short anomaly but we focus on the low-volatility anomaly since it is formed explicitly on the risk characteristic rather than on embedded risks of other anomalies. The AMF model outperforms the Fama–French 5-factor model significantly both in-sample and out-of-sample.