Conventional Regression Techniques Research Articles

Artificial intelligence-driven enhanced CBR modeling of sandy soils considering broad grain size variability

The soil packing, influenced by variations in grain size and the gradation pattern within the soil matrix, plays a crucial role in constituting the mechanical properties of sandy soils. However, previous modeling approaches have overlooked incorporating the full range of representative parameters to accurately predict the soaked California bearing ratio (CBRs) of sandy soils by precisely articulating soil packing in the modeling framework. This study presents an innovative artificial intelligence (AI)-based approach for modeling the CBRs of sandy soils, considering grain size variability meticulously. By synthesizing extensive data from multiple sources, i.e. extensive tailored testing program undertaking multiple tests and extant literature, various modeling techniques including genetic expression programming (GEP), multi-expression programming (MEP), support vector machine (SVM), and multi-linear regression (MLR) are utilized to develop models. The research explores two modeling strategies, namely simplified and composite, with the former incorporating only sieve analysis test parameters, while the latter includes compaction test parameters alongside sieve analysis data. The models' performance is assessed using statistical key performance indicators (KPIs). Results indicate that genetic AI-based algorithms, particularly GEP, outperform SVM and conventional regression techniques, effectively capturing complex relationships between input parameters and CBRs. Additionally, the study reveals insights into model performance concerning the number of input parameters, with GEP consistently outperforming other models. External validation and Taylor diagram analysis demonstrate the GEP models' superiority over existing literature models on an independent dataset from the literature. Parametric and sensitivity analyses highlight the intricate relationships between grain sizes and CBRs, further emphasizing GEP's efficacy in modeling such complexities. This study contributes to enhancing CBRs modeling accuracy for sandy soils, crucial for pertinent infrastructure design and construction rapidly and cost-effectively.

Synthesis of eco-friendly polyaniline-zeolite nanocomposite for pollutant remediation: Empowered by robust machine learning algorithm

The present research assesses the synthesis of an eco-friendly polyaniline and zeolite 4A (4 Armstrong) nanocomposite for enhanced adsorption of dye and heavy metal. Zeolite has been synthesized utilizing natural Kutch-sourced Kaolin clay. The materials synthesized were characterized via various instrumental techniques which confirms the formation of the desired materials. The composite exhibits superior performance in removing hazardous pollutants, demonstrating the removal of 98.5 % chromium in 12 min and 99.8% Congo red in 50 min, individually. Furthermore, for simultaneous removal, the composite continued displaying remarkable performance having a removal rate of 99% and 98.5 % for Congo red and chromium, respectively within 50 min, only. The nanocomposite follows the Freundlich isotherm model for chromium removal indicating physisorption and the Langmuir isotherm model for Congo removal signifying chemisorption. Artificial intelligence and machine learning (ML) techniques have been employed on the data set for the simulation of the adsorption percentage of the synthesized adsorbent. Various uncharted data visualizing techniques, including scatter plots, correlation coefficients, and mutual information were applied to explain the correlation between experimental variables. Conventional regression techniques showed poor performance with a high mean squared error (MSE) of 23 and an R2 value of 0.89. However, Bayesian optimization assisted ML model significantly improved the results. The Gaussian process with a polynomial function was the best performer, achieving an R2 value of 0.99 and mean squared error of 0.008. This research highlights the novel synthesis and effectiveness of the adsorbent materials, demonstrating the potential of machine learning in environmental remediation.

A Novel Hybrid Regression Model for Banking Loss Estimation

Given the critical need to identify financial risks in the banking sector early, this study presents a novel approach that uses historical financial ratios from the FDIC database to predict bank failures in the United States. Accurate estimation of potential losses is essential for risk management and decision-making procedures. We present a novel hybrid approach to loss estimation in the context of bank failures in this study. ElasticNet regression and relevant data extraction techniques are combined in our method to improve prediction accuracy. We conducted thorough experiments and evaluated our hybrid approach's performance against that of conventional regression techniques. With a remarkably low Mean Squared Error (MSE) of 0.001, a significantly high R-squared value of 0.98, and an Explained Variance Score of 0.95, our proposed model demonstrates superior performance compared to existing methodologies. The accuracy of our method is further demonstrated by the Mean Absolute Error (MAE) of 1200 units. Our results highlight the potential of our hybrid approach to transform loss estimation in the banking and finance domain, offering superior predictive capabilities and more accurate loss estimations.

Evaluating the concordance of Egyptian and international sunspot observations

This study provides an exhaustive examination of the evolution of sunspot number (SSN) observations within Egypt, a nation celebrated for its profound astronomical legacy. Although Egypt has a well-established tradition of solar observation, the local SSN records spanning from 2010 to 2022 are compromised by a considerable frequency of absent data, thereby presenting substantial challenges to the precise assessment of solar activity. Addressing this challenge, the study employs dynamic time warping (DTW) as a methodological tool to assess the alignment of local and global SSN datasets. This technique adeptly harmonizes these datasets by reconciling temporal inconsistencies and variations in sampling rates. Subsequent to the application of DTW, the research integrates orthogonal regression for the imputation of the absent values in the Egyptian SSN dataset. This method, preferred for its proficiency in managing errors in both the dependent and independent variables, deviates from conventional linear regression techniques, thereby providing a more nuanced approach to data approximation. The investigation delineates a noteworthy statistical association between the locally-estimated SSN values and the global SSN indices. This correlation is characterized by a consistent pattern in which the locally-derived SSN are systematically lower in comparison to their global counterparts. Nevertheless, these local values display parallel trends and seasonal fluctuations akin to those observed in the global dataset, validating the imputation method and highlighting the unique characteristics of the Egyptian SSN data within the global context of solar activity monitoring. The implications of these findings are significant for the discipline of solar physics, especially for regions contending with incomplete datasets. The methodologies advanced in this research offer a robust framework for the enhancement of datasets with missing data, thus broadening the comprehension of solar phenomena.

Revitalising small tourism destination states: necessity and strategies for structural change in tourism development

ABSTRACT This paper delves into the controversy surrounding the link between structural change and tourism development, particularly focusing on small tourism states, over the period 1995Q1–2020Q4 using a panel-based approach. To address the research objective, the Quantile-on-Quantile (QQ) regression approach is utilised to assess the impact of different quantiles of structural change on the quantiles of tourism development. To ensure robustness, the outcomes of the QQR approach are compared with those of the conventional quantile regression technique. Empirical findings from the QQR approach reveal nuanced relationships. In Belize, Cyprus, Dominican Republic, Iceland, Malta, and Seychelles, structural changes exhibit a structural-increasing effect on tourism development. Conversely, in the Bahamas, Fiji, and Trinidad & Tobago, structural changes manifest both structural-increasing and structural-decreasing effects on tourism development. In Bahrain, structural changes have a structural-decreasing impact on tourism development. Furthermore, the study establishes a feedback nexus between tourism and structural change, offering feasible policy suggestions for policymakers. Overall, the findings suggest that sound policy responses to the relationship between structural change and tourism development should be context-specific, responsive to changing dynamics, and aimed at maximising the positive impacts of structural changes while mitigating potential negative consequences.

Design of a soft sensor based on silver-coated polyamide threads and stress-strain modeling via Gaussian processes

The demand for reliable and efficient soft sensors has grown exponentially with the evolution of wearable devices and smart textiles. However, existing soft sensors often face challenges related to hysteresis, noise, and accuracy, hindering their seamless integration into practical applications. Our research presents a pioneering stress–strain soft sensor model based on silver-coated polyamide threads, augmented with additional silicone and graphite coatings for enhanced properties. Specifically, the silicone coating proves instrumental in elevating the sensor’s gauge factor and reducing noise, resulting in heightened accuracy. The extensive data analysis reveals the presence of hysteresis and non-linearities; however, our data exhibits remarkable robustness, as indicated by the high Spearman correlation coefficient values. In the context of system identification, a comparative analysis between traditional regression methods and Gaussian Process (GPs) Regression demonstrates the superior performance of GPs: this technique outperforms conventional regression techniques, obtaining 8.75 ± 4.06% Root Mean Square Error (RMSE) compared to the 12.70 ± 7.04% error observed in traditional methods. This research not only advances the field of soft sensor technology by developing an accurate, affordable and adaptable device, but also offers valuable insights into highly effective system identification techniques tailored for wearable devices.

Identifying Hidden Factors Associated with Household Emergency Fund Holdings: A Machine Learning Application

This paper describes the results from a study designed to illustrate the use of machine learning analytical techniques from a household consumer perspective. The outcome of interest in this study is a household’s degree of financial preparedness as indicated by the presence of an emergency fund. In this study, six machine learning algorithms were evaluated and then compared to predictions made using a conventional regression technique. The selected ML algorithms showed better prediction performance. Among the six ML algorithms, Gradient Boosting, kNN, and SVM were found to provide the most robust degree of prediction and classification. This paper contributes to the methodological literature in consumer studies as it relates to household financial behavior by showing that when prediction is the main purpose of a study, machine learning techniques provide detailed yet nuanced insights into behavior beyond traditional analytic methods.

Validation of Growth Rate Estimate Using Spline Regression Technique for Green Gram Production in Odisha

The varying pattern of agriculture data in different phases over a long period could be thought of capturing effectively by the spline regression technique. The present study focuses on using spline regression in estimating the growth rate of production of green gram for Odisha. This technique requires the segmentation of the entire study period into distinct periods by inserting knots at suitable intervals. It ensures the same pattern of variation in a particular segment and an abrupt change in the pattern of variation in the next segment. The spline regression approach was compared to the conventional regression technique based on specific statistical criteria to confirm its performance. To estimate the growth rate of green gram in Odisha, spline regression models outperformed conventional regression models, that is why they were chosen for the first and last segments of the study period for area, yield, and output.

Optimizing Faulting Prediction for Rigid Pavements Using a Hybrid SHAP-TPE-CatBoost Model

Faulting refers to the common and significant distress in Jointed Plain Concrete Pavement (JPCP), which has an adverse impact on the pavement roughness. Nevertheless, the existing fault prediction models continue to heavily rely on conventional linear regression techniques or basic machine learning approaches, which leaves room for improvement in training efficiency and interpretability. To enhance training efficiency and accuracy, this study developed five novel faulting prediction models. These models are based on five basic machine learning algorithms: Random Forest (RF), Additive Boosting (AdaBoost), Gradient Boosting Decision Tree (GBDT), Light Gradient Boosting Machine (LightGBM), and Categorical Boost (CatBoost), combined with the tree-structured Parzen estimator (TPE). The five models are TPE-RF, TPE-AdaBoost, TPE-GBDT, TPE-LightGBM, and TPE-CatBoost. In addition to selecting the best-performing model, this study incorporated the Shapley Additive Explanation (SHAP) technique and developed TPE-SHAP-CatBoost to improve the interpretability of the model’s predictions. The process involved extracting historical data on pavement performance, including 17 variables, from the Long-Term Pavement Performance (LTPP) database for 160 instances of observation. Firstly, the Boruta method was used to identify the final set of input variables. Secondly, the TPE technique, which is a Bayesian optimization method, was applied to automatically select the optimal hyperparameters for the base models. Finally, SHAP was used to provide both global and local explanations of the model’s outputs. The results indicate that the TPE-CatBoost model achieves the highest accuracy with an R2 value of 0.906. Furthermore, the TPE-SHAP-CatBoost model identified the primary factors influencing faulting by incorporating SHAP and provided explanations of the model’s results at both the global and local levels. These research findings highlight the ability of the proposed model to accurately predict faulting, providing precise and interpretable guidance for pavement maintenance while reducing workload for pavement engineers in data collection and management.

Health and Socioeconomic Risk Factors for Unplanned Hospitalization Following Ambulatory Unicompartmental Knee Arthroplasty: Development of a Patient Selection Tool Using Machine Learning

BackgroundIdentifying ambulatory surgical candidates at risk for adverse surgical outcomes can optimize outcomes. The purpose of this study was to develop and internally validate a machine learning (ML) algorithm to predict contributors to unexpected hospitalizations after ambulatory unicompartmental knee arthroplasty (UKA). MethodsA total of 2,521 patients undergoing UKA from 2006 to 2018 were retrospectively evaluated. Patients admitted overnight postoperatively were identified as those who had a length of stay ≥ 1 day were analyzed with four individual ML models (ie, random forest, extreme gradient boosting, adaptive boosting, and elastic net penalized logistic regression). An additional model was produced as a weighted ensemble of the four individual algorithms. Area under the receiver operating characteristics (AUROC) compared predictive capacity of these models to conventional logistic regression techniques. ResultsOf the 2,521 patients identified, 103 (4.1%) required at least one overnight stay following ambulatory UKA. The ML ensemble model achieved the best performance based on discrimination assessed via internal validation (AUROC = 87.3), outperforming individual models and conventional logistic regression (AUROC = 81.9-85.7). The variables determined most important by the ensemble model were cumulative time in the operating room, utilization of general anesthesia, increasing age, and patient residency in more urban areas. The model was integrated into a web-based open-access application. ConclusionThe ensemble gradient–boosted ML algorithm demonstrated the highest performance in identifying factors contributing to unexpected hospitalizations in patients receiving UKA. This tool allows physicians and healthcare systems to identify patients at a higher risk of needing inpatient care after UKA.

Validation of Growth Rate Estimate Using Spline Regression Technique for Green Gram Production in Odisha

The varying pattern of agriculture data in different phases over a long period could be thought of capturing effectively by the spline regression technique. The present study focuses on using spline regression in estimating the growth rate of production of green gram for Odisha. This technique requires the segmentation of the entire study period into distinct periods by inserting knots at suitable intervals. It ensures the same pattern of variation in a particular segment and an abrupt change in the pattern of variation in the next segment. The spline regression approach was compared to the conventional regression technique based on specific statistical criteria to confirm its performance. To estimate the growth rate of green gram in Odisha, spline regression models outperformed conventional regression models, which is why they were chosen for the first and last segments of the study period for area, yield, and output. Keywords: Continuity, growth rate, knot, segment, spline regression. JEL Codes: B23, C32, G21.

The impact of board characteristics on the extent of earnings management: conditional evidence from quantile regressions

PurposeThis paper aims to examine the impact of board characteristics on earnings management (EM) among UK non-financial firms.Design/methodology/approachUsing a sample of the UK Financial Times Stock Exchange 350 firms from 2010 till 2019, the authors investigated the relationship between board characteristics (board size, board gender diversity, board tenure, board independence, chief executive office-duality and board meetings) and EM by using the quantile regression technique.FindingsThis study found a non-linear association between board characteristics and discretionary accrual. The empirical evidence showed that board mechanisms reduce the extent of earnings manipulation among UK firms with higher discretionary accruals (DACC) than firms with low and medium DACC levels.Research limitations/implicationsThe results will benefit UK firms by helping them to rethink their board composition. It will also help policymakers understand how the corporate board can help ensure the quality of financial reports.Originality/valueThis study used the quantile regression approach, which helps to clarify the mixed findings of prior studies that used conventional regression techniques.

Unraveling the effects of hydrological connectivity and landscape characteristics on reservoir water quality

Dam construction and reservoir operation altered the landscape and hydrological process of reservoir bays, affecting reservoir water quality. However, many landscape and hydrological connectivity metrics are highly correlated and may introduce redundancies and misleading results when use conventional multivariate regression techniques. Knowledge concerning the pure effects of landscape and hydrological connectivity metrics are crucial for understanding nonpoint pollution processes and guiding water quality protection strategies in reservoirs. Based on water quality monitoring data for six years (2015–2020) from 66 reservoir bays of the Danjiangkou Reservoir in China during both flood discharge periods (FDPs) and water storage periods (WSPs), machine learning approaches (boosted regression trees and random forest) were conducted to decipher the effects of hydrological connectivity and landscape characteristics on water quality. The results showed that landscape composition, landscape configuration, and topography had the combined importance of 46.69%, 31.48%, and 10.14% on the overall water quality changes during the FDPs, respectively. However, landscape configuration was the largest importance factor controlling overall water quality for the WSPs with the combined importance of 38.57%. For the FDPs, the top two importance variables of overall water quality variation were the proportions of shrub and agricultural land in the reservoir bay. For the WSPs, the top two importance variables were flow length and index of connectivity. For specific water quality parameters, the highest importance factor controlling the variation in total nitrogen, total phosphorus, ammonia nitrogen, nitrate and chlorophyll a were landscape configuration, while the landscape composition had the highest importance on the variation in permanganate index, suggesting landscape characteristics affected water quality with specific responses to distinct water quality parameters. These findings emphasize the distinct roles of landscape and hydrological characteristics on water quality and provide important information for the efficient formulation of water quality protection strategies in reservoirs.

Infrared spectroscopy of quasi-ideal binary liquid mixtures: The challenges of conventional chemometric regression

We have recorded ATR-IR spectra of binary mixtures in the (quasi-)ideal systems Benzene-Toluene, Benzene-Carbon tetrachloride and Benzene-Cyclohexane and performed classical least squares, inverse least squares and principal component regression on the resulting spectra. In contrast to the general expectation, the spectra of ideal mixtures follow only roughly Beer’s approximation, in particular stronger bands show shifts and increased intensities for intermediary compositions since the polarization of matter by light cannot be neglected. As a consequence, these conventional regression techniques lead to principle and unavoidable errors, even though some of the classical regression techniques are assumed to be able to cope with nonlinearities. In particular in the system Benzene-Carbon tetrachloride large errors result and the relative average error of the volume fraction determination is about 10 % for all three methods. Especially remarkable is that the multivariate regression methods do not perform better than the classical univariate calibration if for the latter a peak due to an oscillator with comparably low oscillator strength is selected, since for such bands polarization effects are weak and Beer’s approximation holds comparably well.

Brain drain in microfinance institutions: the role of gender and organizational factors

PurposeUncontrollable brain drain (employees’ turnover) has been found to hamper humanitarian and sustainable objectives of socially oriented organizations. Hence, this study aims to explore the roles of gender and organizational-level factors on the rate of employees’ turnover in microfinance institutions (MFIs).Design/methodology/approachThe study used an unbalanced panel data of 235 MFIs spanning the period 2010–2019. Based on the availability of the required data set on the World Bank catalogue (in collaboration with Microfinance Information Exchange-MIX Market), this study covers four South Asian countries, namely, Bangladesh, India, Pakistan and Sri Lanka. Then, the authors analyzed the data using the conventional panel data regression techniques (e.g. fixed effects model and random effects model).FindingsThe regression results revealed that women leaders (board members) could significantly reduce the employee turnover rate of MFIs. Although the efficiency wage hypothesis is supported in this study, it depends on the profit orientation of the MFIs. This study also confirmed that financial sustainability and donations have helped MFIs to reduce their employees’ turnover, which reiterates the image and brand value effect of MFIs. Moreover, the overall gender development and legal status (e.g. Bank and Non-Bank Financial Institutions) have also been found to have an effect on employees’ turnover based on the sub-sample analysis.Originality/valueTo the best of the authors’ knowledge, the study is among the first to investigate the impact of gender and institutional characteristics on employees’ turnover based on a large and recent panel dataset from selected South Asian countries.

A Machine Learning-Based QSAR Model for Quinolines Tested As Corrosion Inhibitors of Mild Steel in HCl Solution

The investigation of organic compounds as potential inhibitors of metal corrosion using several experimental and/or computational techniques has been well established in literature. Recent advances in the development of corrosion inhibitors has led to the exploration of quantitative structure activity relationship (QSAR) as a worthy alternative to the rigorous, sometimes expensive and time-consuming experimental/computational procedures. QSAR is a robust computational method that generates mathematical models that maps the structural features of organic compounds with their inhibition performances. The obtained mathematical models can then be further used to predict the chemical activity of new and untested organic molecules. Although linear and non-linear methods have been reported in developing QSAR models, only few works have explored the use of state-of-the-art artificial neural network (ANN). This study reports the development of QSAR models for sixty quinolines investigated as corrosion inhibitors for mild steel corrosion in 1 M HCl using both linear and non-linear modelling techniques. Density functional theory (DFT) and Dragon 7 software were used to generate molecular descriptors for model development and were reduced to a significant few using feature selection tools. The significant molecular descriptors were employed in model building using conventional multiple linear regression (MLR) and ANN modelling techniques. The developed models were evaluated using several statistical performance metrics and the ANN-based model was found to produce the best correlation between the predicted and experimental inhibition efficiencies. Furthermore, nine new quinoline molecules were theoretically designed and their inhibition efficiencies were predicted using the best developed ANN model.

Confinement model for LRS FRP-confined concrete using conventional regression and artificial neural network techniques

Concrete confined using fiber-reinforced polymer (FRP) composites experience significant enhancements in strength and strain. For the seismic retrofitting of existing reinforced concrete (RC) structures, a large rupture strain (LRS) FRP (i.e., polyethylene terephthalate and naphthalate, denoted as PET and PEN respectively), with a larger rupture strain of more than 5%, is a promising alternative to conventional FRPs with a rupture strain of less than 3%. The majority of analytical models on the stress–strain behavior of FRP-confined concrete under axial compression have focused largely on concrete confined with the traditional FRP material. Analytical research on LRS FRP-confined concrete is, however, limited. Moreover, all existed stress–strain models were determined based on theoretical analysis and test data fitting. In this paper, the artificial neural networks (ANN) method is employed to build a confinement model directly from experimental data to predict the different components of the stress–strain response. A test database consisting of 226 axial compression tests on LRS FRP-confined concrete specimens is used. The test results, in terms of full confined stress–strain response, strength, strain, FRP rupture strain, and dilation response were investigated. Predictive expressions and practical ANN models for the strength, strain, and shape of an axial stress–strain response are provided. Existing models for LRS FRP-confined concrete were also evaluated. The results of the existing and proposed models report that the proposed methods achieve significantly better results.

What do you know and how much does it matter? A QCA/NCA study of knowledge and supplier performance

While interorganizational research has emphasized the role of governance mechanisms in managing the performance of suppliers that provide critical input components, scholarship consistently assumes that these governance mechanisms work independent of how much the supplier knows or how much the buyer knows. Contributing to this body of work, we explore two important boundary conditions to the association between governance mechanisms and supplier performance: the buyer’s knowledge of the outsourced component and the supplier’s technical expertise. In doing so, our theory integrates recent insights from the literature on concurrent sourcing, which acknowledges that firms often make and buy the same input. Methodologically, we draw on configurational methods of fuzzy set Qualitative Comparative Analysis (fsQCA) and Necessary Conditional Analysis (NCA), given that conventional regression techniques fall short in analyzing the complex interrelationships predicted by our theory. Our analysis provides interesting and novel insights. Broadly, we find that deploying concurrent sourcing in conjunction with formal and relational governance mechanisms leads to high supplier performance, even when the supplier himself is less technical capable. However, concurrent sourcing is no guarantee for high performance, as a concurrent sourcing firm who deals with a non-expert supplier is doomed to low performance when relational governance mechanisms are absent. Overall, our analysis of firm and supplier knowledge in orchestration with established governance mechanisms underscores the value of configurational approaches to management research.

Machine learning for developing a prediction model of hospital admission of emergency department patients: Hype or hope?

ObjectiveEarly identification of emergency department (ED) patients who need hospitalization is essential for quality of care and patient safety. We aimed to compare machine learning (ML) models predicting the hospitalization of ED patients and conventional regression techniques at three points in time after ED registration. MethodsWe analyzed consecutive ED patients of three hospitals using the Netherlands Emergency Department Evaluation Database (NEED). We developed prediction models for hospitalization using an increasing number of data available at triage, ∼30 min (including vital signs) and ∼2 h (including laboratory tests) after ED registration, using ML (random forest, gradient boosted decision trees, deep neural networks) and multivariable logistic regression analysis (including spline transformations for continuous predictors). Demographics, urgency, presenting complaints, disease severity and proxies for comorbidity, and complexity were used as covariates. We compared the performance using the area under the ROC curve in independent validation sets from each hospital. ResultsWe included 172,104 ED patients of whom 66,782 (39 %) were hospitalized. The AUC of the multivariable logistic regression model was 0.82 (0.78−0.86) at triage, 0.84 (0.81−0.86) at ∼30 min and 0.83 (0.75−0.92) after ∼2 h. The best performing ML model over time was the gradient boosted decision trees model with an AUC of 0.84 (0.77−0.88) at triage, 0.86 (0.82−0.89) at ∼30 min and 0.86 (0.74−0.93) after ∼2 h. ConclusionsOur study showed that machine learning models had an excellent but similar predictive performance as the logistic regression model for predicting hospital admission. In comparison to the 30-min model, the 2-h model did not show a performance improvement. After further validation, these prediction models could support management decisions by real-time feedback to medical personal.

Factors affecting borrowers’ turnover in microfinance institutions: A panel evidence

AbstractIn the era of competitiveness, clients or borrowers remain an important asset for financial institutions, as they are the ultimate source of revenue. Although the departure of clients from one microfinance institution (MFI) to another is a common phenomenon, the manner in which organizational characteristics affect turnover is largely unknown in the context of the microfinance industry. Hence, by utilizing recent (2010–18) data on 235 MFIs from the global microfinance industry, this study investigates the factors affecting the borrower turnover rates (BTR) of MFIs by employing conventional panel regression techniques. To overcome endogeneity and ensure robust and dynamic results, the generalized method of moments (GMM) has also been used in this study. The findings reveal that the efficiency‐wage and financial self‐sufficiency of MFIs reduce BTR, while staff turnover rate, write‐off ratio and average loan size increase BTR. Our results remain robust even after controlling for several market and macro‐economic factors. The findings could be utilized to generate several policy implications to reduce borrowers’ turnover.