A Case Study of University Students' Performance in Arabic and Islamic Culture Courses Before and During the Pandemic (Face-to-Face and Online Instruction)

In the present study, we examined whether students' academic success in courses devoted to Arabic and Islamic culture changed when the familiar face-to-face delivery format (before the Covid-19 pandemic) was discarded in favor ofan online synchronous delivery format (during the pandemic). The final class grades of students enrolled in one of four courses in a sequence devoted to Arabic culture and religion were compared while holding constant the variable instructor. The ability of early performance indicators to predict final class grades was also examined to assess whether there were differences between instructional deliveries. Superior performance and lower failure rates were observed online for courses at the beginning of the sequence, but not at the end of the sequence. These findings suggest that the impact of instructional delivery might vary depending on the students' accumulated academic experience.

The Relationship Between Financial Indicators and Financial Intermediaries' Stock Price Volatility Listed on the BM&FBOVESPA Index in the Crisis Period of 2008 and 2020 (Covid-19): GCG

The study goal was to verify the relationship among financial indicators and intermediaries' volatility stock price listed on the BM&FBovespa Index in the crisis period from 2008 and 2020 (COVID-19). The methods used for analysis were Spearman's correlation, multiple linear regression, and Test T. The analyzed period refers to the year 2008, the second semester of 2019 and the first semester of 2020, which include the periods before and during the crises of 2008 and 2020. The results found show that only the indicator of the assets total turnover rate has a significant relationship with the stock price volatility.Alternate :O estudo tem como objetivo verificar a relação entre os indicadores com a volatilidade das ações das intermediadoras financeiras listadas no Índice BM&FBovespa no período das crises de 2008 e 2020 (COVID-19). Os métodos utilizados para análise foram de correlação de Spearman, regressão linear múltipla e Teste T. O período analisado refere-se ao ano de 2008, segundo semestre de 2019 e primeiro semestre de 2020, onde englobam os períodos pré e durante as crises de 2008 e 2020. Os resultados encontrados apontam que apenas o indicador taxa total de rotatividade dos ativos possui relação significativa com a volatilidade do preço das ações.Alternate :El estudio tiene como objetivo verificar la relación entre los indicadores y la volatilidad de las acciones de los intermediarios financieros listados en el Índice BM&FBovespa en el período de las crisis de 2008 y 2020 (COVID-19). Los métodos utilizados para el análisis fueron la correlación de Spearman, la regresión lineal múltiple y la prueba T. El período analizado se refiere al año 2008, la segunda mitad de 2019 y la primera mitad de 2020, que incluyen los períodos antes y durante las crisis de 2008 y 2020. Los resultados encontrados indican que solo el indicador de tasa de rotación de activos totales tiene una relación significativa con la volatilidad del precio de las acciones.

Airline catering supply chain performance during pandemic disruption: a Bayesian network modelling approach

PurposeThe supply chain (SC) encompasses all actions related to meeting customer requests and transferring materials upstream to meet those demands. Organisations must operate towards increasing SC efficiency and effectiveness to meet SC objectives. Although most businesses expected the coronavirus disease 2019 (COVID-19) pandemic to severely negatively impact their SCs, they did not know how to model disruptions or their effects on performance in the event of a pandemic, leading to delayed responses, an incomplete understanding of the pandemic's effects and late deployment of recovery measures. Therefore, this study aims to consider the impact of implementing Bayesian network (BN) modelling to measure SC performance in the airline catering context.Design/methodology/approachThis study presents a method for modelling and quantifying SC performance assessment for airline catering. In the COVID-19 context, the researchers proposed a BN model to measure SC performance and risk events and quantify the consequences of pandemic disruptions.FindingsThe study simulates and measures the impact of different triggers on SC performance and business continuity using forward and backward propagation analysis, among other BN features, enabling us to combine various SC perspectives and explicitly account for pandemic scenarios.Originality/valueThis study's findings offer a fresh theoretical perspective on the use of BNs in pandemic SC disruption modelling. The findings can be used as a decision-making tool to predict and better understand how pandemics affect SC performance.

Computational Intelligence and Soft Computing Paradigm for Cheating Detection in Online Examinations

Covid-19 has been a life-changer in the sphere of online education. With complete lockdown in various countries, there has been a tumultuous increase in the need for providing online education, and hence, it has become mandatory for examiners to ensure that a fair methodology is followed for evaluation, and academic integrity is met. A plethora of literature is available related to methods to mitigate cheating during online examinations. A systematic literature review (SLR) has been followed in our article which aims at introducing the research gap in terms of the usage of soft computing techniques to combat cheating during online examinations. We have also presented state-of-the-art methods followed, which are capable of mitigating online cheating, namely, face recognition, face expression recognition, head posture analysis, eye gaze tracking, network data traffic analysis, and detection of IP spoofing. A discussion on improvement of existing online cheating detection systems has also been presented.

Value stream mapping from the customer's perspective: expanding concepts, representations and key performance indicators based on a typical real case study

PurposeThis study aims to improve the buying experience for both customers and providers by presenting a conceptual basis which seeks to expand the usual understanding, representation, mapping and measurements of the different value and non-value stages of a customer purchase journey (CPJ).Design/methodology/approachInspired by the precepts of lean thinking, with emphasis on the value stream mapping method, the approach is based on an in-depth analysis of a real and typical e-commerce acquisition of an electronic customised product (a mobile phone) during the COVID-19 pandemic.FindingsThis study demonstrates different types of consumer stages, values and wastes for the CPJ. This allowed the development of a mathematical formulation – named customer journey engineering (CJE) – from which improvements of the different categories can be identified. Exemplifying with those whose implementations require no further efforts or costs, the following results could be readily obtained in the case studied: a reduction of 96 h of non-value activities, an improvement of approximately 15% of the established index for customer satisfaction and avoidance of loss worth US$50 for the analysed customer.Research limitations/implicationsThe consistency and applicability of the qualitative and quantitative findings presented here should be examined further in other customer purchase scenarios, allowing enhancements of the CJE approach.Originality/valueRegardless of the context in question, this investigation attempts to identify and precisely define any common universal elements, often overlooked, which constitute the structure of any CPJ and are crucial for its understanding and improvement.

The role of cognitive capital in supply chain resilience: an investigation during the COVID-19 pandemic

PurposeResearch on the "black box” of cognitive capital remains limited in supply chain resilience (SCRES) literature. Drawing from an in-depth single case study of a major consumer electronics multinational facing the COVID-19 disruption, this paper aims to develop a clearer picture of cognitive capital's elements while contextualizing how they interact with SCRES temporal capabilities to prepare, respond, recover and learn.Design/methodology/approachConsisting of 40 in-depth interviews collected during a four-month period, this single case revolves around the buyer's view across 36 multiregional buyer–supplier dyads, spanning 17 product and service categories. Data were processed during the pandemic, while findings discuss pre- and intra-crisis events based on two scenarios: the impact of disruption on category demand, comparing sudden pandemic-driven product and service demand fluctuations (i.e. increase, decrease);and the geographical proximity of the supplier relative to the buying firm.FindingsThe case unveils different elements of cognitive capital (e.g. shared goals, assumptions, values, kinesics language, multilingualism, virtual negotiation, prior disruption experience, shared process capabilities) during a major global disruption, suggesting that different cognitive capital elements influence positively and differently SCRES' temporal capabilities. Overall, buying firms are urged to build on cognitive capital to improve SCRES preparation, response, recovery and learning.Originality/valueThis paper extends the understanding of cognitive capital in buyer–supplier relationships by identifying its elements and offering a theoretical articulation of how they enable episodically the four SCRES temporal capabilities under contingencies of increased and decreased demands, and suppliers' geographical proximity.

Guest editorial: The future of family business: marketing challenges in times of crisis

[...]decision-makers face new conditions that affect their reasoning and their customer validation, forcing them to reframe their marketing operations (Syam and Sharma, 2018). [...]this issue contributes to family firm research. The third paper, "Assessing the AI-CRM technology capability for sustaining family businesses in times of crisis: the moderating role of strategic intent”, by Ranjan Chaudhuri Sheshadri Chatterjee, Sascha Kraus and Demetris Vrontis, investigates the potential for artificial-intelligence-integrated customer relationship management (AI-CRM) technology to sustain family businesses in times of crisis, assessing the moderating role of strategic intent. The sixth article, entitled "Effective business model adaptations in family SMEs in response to the COVID-19 crisis”, by Sofia Brunelli, Rafaela Gjergji, Valentina Lazzarotti, Salvatore Sciascia and Federico Visconti, tested the effects of two major business model adaptations – namely changes in value proposition and changes in target market – on a sample of 96 family SMEs.

An intelligent framework for analyzing supply chain resilience of firms in China: a hybrid multicriteria approach

PurposeThe paper aims to identify the most supply chain resilient company suitable for the customized preferences of partner firms in the context of the Chinese supply chain framework during the COVID-19 pandemic.Design/methodology/approachA hybrid multicriteria model, i.e. Fuzzy Analytical Hierarchy Process (AHP), was used to assign weights to each criterion, which was subsequently analyzed by three approaches, namely Fuzzy Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), Fuzzy DEMATEL (Decision-Making Trial and Evaluation Laboratory), and Evaluation Based on Distance from Average Solution (EDA), to rank the top ten companies in descending order of supply chain resilience. Further, sensitivity analysis is performed to identify the consistency in ranking with variation in weights. The rankings are validated by a novel Ensemble Ranking algorithm and by supply chain domain experts.FindingsThe rankings suggest the company "China Energy Construction Group Tianjin Electric Power Construction Co., Ltd” is the most feasible and resilient company, presenting interesting findings to partner firms, and Bosch is the least reliable supply chain company of the ten firms considered, thus presenting interesting findings to partner companies.Practical implications"Crisis Management Beforehand” is most critical in the current pandemic scenario. This implies that companies need to first prioritize taking proactive steps in crisis management followed by the need to minimize the "Expected impact of pandemic.” Performance factors also need to be regulated (sales, supply chain rank and financial performance) to maintain the company's overall reputation. Considering the consistent performance of the China Energy Construction Group Tianjin Electric Power Construction Co., Ltd., it is recommended as the most reliable supply chain firm to forge strategic partnerships with other supply chain stakeholders like suppliers and customers. On the other hand, Bosch is not recommended as a supply chain reliable company and needs to improve its crisis management capabilities to minimize the pandemic impact.Originality/valueThe paper aims to identify the most supply chain resilient company suitable for the customized preferences of partner firms in the context of the Chinese supply chain framework during the COVID-19 pandemic. The rankings suggest the company "China Energy Construction Group Tianjin Electric Power Construction Co., Ltd” is the most feasible and resilient company, presenting interesting findings to partner firms, and Bosch is the least reliable supply chain company of the ten firms considered, thus presenting interesting findings to partner companies.

Person Identification and Gender Classification Based on Vision Transformers for Periocular Images

Simple SummaryThe idea of identifying persons using the fewest traits from the face, particularly the area surrounding the eye, was carried out in light of the present COVID-19 scenario. This may also be applied to doctors working in hospitals, the military, and even in certain faiths where the face is mostly covered, except the eyes. The most recent advancement in computer vision, called vision transformers, has been tested for the UBIPr dataset for different architectures. The proposed model is pretrained on an openly available ImageNet dataset with 1 K classes and 1.3 M pictures before using it on the real dataset of interest, and accordingly the input images are scaled to 224 × 224. The PyTorch framework, which is particularly helpful for creating complicated neural networks, has been utilized to create our models. To avoid overfitting, the stratified K-Fold technique is used to make the model less prone to overfitting. The accuracy results have proven that these techniques are highly effective for both person identification and gender classification.AbstractMany biometrics advancements have been widely used for security applications. This field's evolution began with fingerprints and continued with periocular imaging, which has gained popularity due to the pandemic scenario. CNN (convolutional neural networks) has revolutionized the computer vision domain by demonstrating various state-of-the-art results (performance metrics) with the help of deep-learning-based architectures. The latest transformation has happened with the invention of transformers, which are used in NLP (natural language processing) and are presently being adapted for computer vision. In this work, we have implemented five different ViT- (vision transformer) based architectures for person identification and gender classification. The experiment was performed on the ViT architectures and their modified counterparts. In general, the samples selected for train:val:test splits are random, and the trained model may get affected by overfitting. To overcome this, we have performed 5-fold cross-validation-based analysis. The experiment's performance matrix indicates that the proposed method achieved better results for gender classification as well as person identification. We also experimented with train-val-test partitions for benchmarking with existing architectures and observed significant improvements. We utilized the publicly available UBIPr dataset for performing this experimentation.

ESG (ÇEVRESEL, SOSYAL VE KURUMSAL YÖNETÍM) SKORUNUN FÍRMA PERFORMANSINA ETKÍSÍ: TÜRK BANKACILIK SEKTÖRÜ ÖRNEĞÍ

ESG skorları, firmaların çevresel, sosyal ve kurumsal yönetim alanlarındaki yatırım ve faaliyetleri ile ilgili performansını ortaya koyan bir ölçüttür. Son yıllarda firmaların paydaşlardan gelen talepleri dikkate alarak çeşitli raporlama modelleri geliştirmesi sonucunda ortaya çıkan bu kavram, tüm paydaşların finansal kararları üzerinde daha fazla belirleyici olmaya başlamıştır. Bu çalışmanın amacı Türkiye'de faaliyet gösteren mevduat bankalarında ESG skorlarının finansal performans üzerindeki etkisini araştırmaktır. Çalışma 2010-2020 dönemini kapsamaktadır. PCSE ve FGLS panel veri tahmincileri kullanarak yapılan analizlerde, bankaların toplam ESG, sosyal (SPS) ve kurumsal yönetim (GPS) skorlarının muhasebe ve piyasa temelli performans göstergelerini (ROA ve Tobin Q) pozitif yönde etkilediği tespit edilmiştir. Diğer taraftan çevresel (EPS) skorunun her iki performans göstergesi üzerinde de istatistiksel olarak anlamlı bir etkiye sahip olmadığı görülmüştür. Ayrıca sonuçlar, Covid-19 pandemisinin bankaların ROA ve Tobin Q ile ölçülen performanslarında azalışa yol açtığını göstermektedir. Analiz bulguları firma performansını artırmada finansal olmayan raporlamaya ve ESG faaliyetlerine daha fazla önem verilmesi gerektiğini işaret etmektedir.Alternate :ESG scores are a measure that reveals the performance of companies regarding their investments and activities in the fields of environmental, social, and corporate governance. In recent years, this concept, which emerged because of companies developing reporting models by considering the demands from stakeholders, has begun to become more decisive on the financial decisions of all stakeholders. The aim of this study is to investigate the effect of ESG scores on financial performance of Turkish commercial banks in the period of 2010-2020. In the analyzes performed using the PCSE and FGLS panel data estimators, it has been concluded that the total ESG, social (SPS) and corporate governance (GPS) scores of the banks positively affect the accounting and market-based performance indicators (ROA and Tobin's Q). On the other hand, it was seen that the environmental (EPS) score did not have a statistically significant effect on both performance indicators. In addition, the results show that the Covid-19 pandemic has led to a decrease in banks' performance as measured by ROA and Tobin's Q. Analysis outcomes indicate that giving more importance to non-financial reporting and ESG activities will contribute to enhancing firm performance.

SMEs Managers' Perceptions of MCS: A Mixed Methods Approach

The goals of this study are to explore the use of the Management Control Systems (MCS) by SMEs' managers at the country level in order to identify the importance given to financial and nonfinancial measures, as well as key performance indicators. In this study, we use the behavioral accounting lens and adopt mixed methods approach to study the use of the MCS in Portuguese small to medium enterprises (SMEs): a correlational and a configurational analysis. Data was collected from a cross-sectional survey of 414 top managers of Portuguese SMEs across several industries. The results show that managers' perceptions of the importance given to financial measures is positively and significantly related to the importance given to several nonfinancial measures. We take an original approach by addressing the managers' perceptions to contribute to the understanding of Portuguese SMEs' use of tools for strategy implementation: the use of different MCS. Additionally, the study discovers alternative configurations of individual and organizational conditions that lead to the managers' perception of the importance given to financial and nonfinancial measures. This paper offers support for SMEs based on controlling strategy implementation by using MCS. The study's limitations regard a relatively low response rate to the questionnaire (4.56%), which may be justified because data was collected during the COVID-19 pandemic. We offer alternative configurations that generate the perception of managers about the importance of using financial and nonfinancial measures. Our results enlighten the use of such tools in support of strategic accomplishment.

Bank-specific performance indicators, macroeconomic variables and capital adequacy of Nigerian banking industry

[...]we canvass those Nigerian banks should reduce dividend payouts and increase retained profits as a buffer against exposed risks. To ensure the healthiness of banks in the banking industry as well as facilitate international transaction, the central bank of ten countries (Belgium, Canada, France, Germany, Italy, Japan, the Netherlands, Sweden, the UK and the US) formed the committee of banking supervision in 1988 (the Basel Committee on Banking Supervision). Since the formation of this committee, it has undergone at least three stages called the Basel I, Basel II and Basel III. Premised on shock to the economy brought on by the coronavirus pandemic, with economic growth in 2020 expected to contract by as much as 4.4 percent to 8.94 percent, a drop in oil receipt and a devalued Naira in the range of 380-450 to US dollar, the capital adequacy of banks could be severely threatened, (Egba, 2020). [...]scholars have extensively shown that bank specific performance indicators and macroeconomic factors affected capital adequacy ratio. [...]this paper examined the effect of banks specific-performance indicators and macroeconomic factors on bank financing which is the minimum funds required for their short-term obligation or capital adequacy ratio.

Strategic Analysis of Financial and Operational Data During a Global Economic Crisis: Lessons from the COVID-19 Pandemic

Assessing the operational efficiency and financial health of a company, from a Strategic Management perspective, is a major challenge even during normal times. The economic crisis and its associated uncertainties, caused by the Covid-19 pandemic, have made these challenges even more daunting for business students, faculty, and professional analysts alike. In this paper, we first review the broad impact that the pandemic has inflicted on the industrial and economic climate globally. We then take an in-depth look at two representative industries and analyze how they have been impacted by the crisis. Specifically, we look at the airlines industry and the restaurants and food delivery industry, by reviewing and interpreting a select set of financial and operational metrics pre-crisis, during a crisis, and the post / recovery stages of a crisis. We look at performance indicators in these two industries and identify which metrics might provide us with the sharpest insights on the future performance of companies in these industries. We also provide more general guidelines for analysis of companies across other industries, their inter-connectedness, and the ecosystems that they operate in.

Guest editorial: KPIs to help develop the next normal in construction practice, teaching-learning and research

[...]this special issue contributes to priming the construction industry for the next normal by re-examining the emerging needs for reengineering or developing novel and more relevant key performance indicators (KPIs) to better measure the performance of construction projects, online teaching-learning and research following vast digital and other transformations triggered, if not accelerated by the COVID-19 pandemic. [...]virtual FAT (vFAT) became a popular substitute for physical FAT. The paper showed construction digitisation such as VR, augmented reality (AR) and building information modelling (BIM) is highly cooperative as it can easily be made available for online learning. [...]the findings support construction educators to use online-based VR learning to promote efficient teaching of design buildability to students. The research papers cover findings related to a wide range of countries such as India, Malaysia, New Zealand, South Africa, Sri Lanka and USA, and the authors of the papers also represent several different institutions within or across countries. [...]this special issue provides a snapshot of various KPIs and metrics proposed for the next normal in construction, considering different contextual factors experienced by various different geographical regions across the world.

A review of methodologies for performance evaluation of automated construction processes

Purpose>The aim of this paper is to synthesize knowledge related to performance evaluation of automated construction processes during the planning and execution phases through a theme-based literature classification. The primary research question that is addressed is “How to quantify the performance improvement in automated construction processes?”Design/methodology/approach>A systematic literature review of papers on automated construction was conducted involving three stages-planning, conducting and reporting. In the planning stage, the purpose of the review is established through key research questions. Then, a four-step process is employed consisting of identification, screening, shortlisting and inclusion of papers. For reporting, observations were critically analysed and categorized according to themes.Findings>The primary conclusion from this study is that the effectiveness of construction processes can only be benchmarked using realistic simulations. Simulations help to pinpoint the root causes of success or failure of projects that are either already completed or under execution. In automated construction, there are many complex interactions between humans and machines;therefore, detailed simulation models are needed for accurate predictions. One key requirement for simulation is the calibration of the models using real data from construction sites.Research limitations/implications>This study is based on a review of 169 papers from a database of peer-reviewed journals, within a time span of 50 years.Originality/value>Gap in research in the area of performance evaluation of automated construction is brought out. The importance of simulation models calibrated with on-site data within a methodology for performance evaluation is highlighted.

Enhanced K-Means ++ Using Probability Theory For Efficient Prediction Of Air Pollution

Increasing concentrations of air pollutants is a global concern as it is a major underlying cause for other serious issues like premature deaths, global warming, increased susceptibility to heart diseases, lung disorders and skin disorders. Exposure to particulate pollutants increases vulnerability to Covid-19 and risk of succumbing to the virus. Air pollution analysis is a widely undertaken study by government officials and research scholars. K-means is a frequently used algorithm to understand the condition of the atmosphere from massive sensor generated data. The algorithm however comes with its drawbacks. Random initialization of the initial centroids can lead to bad clustering, an alternative, K-means++ does away with this, however, takes more execution time and iterations which is not ideal. We propose an advanced K-means++ initialization algorithm which incorporates an oversampling factor for smarter initialization of centroids using probability theory and weight assignment. We also propose a probability based convergence algorithm as opposed to the regular convergence algorithm to smartly select a portion of the data points to recompute the centroids. This will ensure a faster formation of final clusters. Real time Bengaluru, India air pollution data is scraped, pre-processed and clustered using the proposed technique. All the variants of K-means under study are compared over parameters of execution time, iterations and performance metrics. This work is also extended to tackle future air data points using a fast ensemble model. The solution proposed is better in terms of being reliable, fast and helps with better clustering, which leads to better air quality analysis, which leads to better air quality prediction, which leads to taking apt precautions to mitigate and regulate the air pollution.

Directions of Stimulation of the Development of Tourism Infrastructure by Attraction of Investments

This article notes that the uncertainty of the consequences of the pandemic has shown the need for the development of domestic tourism, the creation of modern health resort and tourism services and improving the quality of tourism infrastructure by attracting investments for maintenance and provision of transport and the development of tourism products and services, the introduction of environmental protection measures. Using the given statistical data on the development of the tourism and hospitality industry of the Republic of Kazakhstan, the authors analyzed the influence of some factors influencing the development of the tourism industry. The indicators of the structure of the population's expenditures on paid services, the distribution of resident visitors by purpose of travel at places of accommodation for 2021, the number of visitors served at places of accommodation for tourists in general in Kazakhstan, the main indicators of financial and economic activities in the field of tourism for 2016-2021 are given, performance indicators of tourist infrastructure facilities for the analyzed period. Proposals are given for the transformation of the most significant tourist sites included in the Touristification Map of Kazakhstan into one tourist cluster with a unique dominant experimental structure with transfer to foreign tourism markets in the future.

Sustainable Assessment in Supply Chain and Infrastructure Management

Assessing sustainability in supply chain and infrastructure management is important for any organization in the competitive business environment or public domain. Public buildings such as higher education institutions are responsible for a substantial portion of energy consumption and anthropogenic greenhouse gas (GHG) emissions. Roukouni et al. (contribution twelve) developed truck platooning and multi-sided digital platforms games for barge transportation, both improving the sustainability of hinterland transportation. Besides these studies, Özdemir et al. (contribution thirteen) assessed the efficiency of the operations strategy matrix in the healthcare system amid COVID-19.

ANALYSIS OF THE CORRELATIONS BETWEEN THE DEGREE OF INDEBTEDNESS AND THE PERFORMANCE OF THE ECONOMIC ENTITIES FROM EMERGING ECONOMY

The purpose of this research is to assess the performance of the economic entities that are part of the BRICS economies (Brazil, Russia, India, China, South Africa). Thus, the following objectives have been set to achieve the intended purpose: O1 - analysis and evaluation of the economic performance that were reported by entities in the emerging BRICS economies;O2 - identification of the correlations between the performance indicators that were reported by entities from emerging BRICS economies (Return on Assets;level of indebtedness;equity ratio;Earnings Before Interest, Taxes, Depreciation, and Amortization growth). For these objectives to be achieved, we have collected and analyzed the financial data from the reports of 50 companies that are listed on a regulated market in Brazil, Russia, India, China and South Africa. This research focuses on assessing the effects of the financial report and of the level of indebtedness on the performance of the entities from emerging BRICS economies. Research is relevant to current and potential investors interested in emerging BRICS economies, as well as for other categories of stakeholders.

Identifying Protein Features and Pathways Responsible for Toxicity Using Machine Learning and Tox21: Implications for Predictive Toxicology

Humans are exposed to numerous compounds daily, some of which have adverse effects on health. Computational approaches for modeling toxicological data in conjunction with machine learning algorithms have gained popularity over the last few years. Machine learning approaches have been used to predict toxicity-related biological activities using chemical structure descriptors. However, toxicity-related proteomic features have not been fully investigated. In this study, we construct a computational pipeline using machine learning models for predicting the most important protein features responsible for the toxicity of compounds taken from the Tox21 dataset that is implemented within the multiscale Computational Analysis of Novel Drug Opportunities (CANDO) therapeutic discovery platform. Tox21 is a highly imbalanced dataset consisting of twelve in vitro assays, seven from the nuclear receptor (NR) signaling pathway and five from the stress response (SR) pathway, for more than 10,000 compounds. For the machine learning model, we employed a random forest with the combination of Synthetic Minority Oversampling Technique (SMOTE) and the Edited Nearest Neighbor (ENN) method (SMOTE+ENN), which is a resampling method to balance the activity class distribution. Within the NR and SR pathways, the activity of the aryl hydrocarbon receptor (NR-AhR) and the mitochondrial membrane potential (SR-MMP) were two of the top-performing twelve toxicity endpoints with AUCROCs of 0.90 and 0.92, respectively. The top extracted features for evaluating compound toxicity were analyzed for enrichment to highlight the implicated biological pathways and proteins. We validated our enrichment results for the activity of the AhR using a thorough literature search. Our case study showed that the selected enriched pathways and proteins from our computational pipeline are not only correlated with AhR toxicity but also form a cascading upstream/downstream arrangement. Our work elucidates significant relationships between protein and compound interactions computed using CANDO and the associated biological pathways to which the proteins belong for twelve toxicity endpoints. This novel study uses machine learning not only to predict and understand toxicity but also elucidates therapeutic mechanisms at a proteomic level for a variety of toxicity endpoints.