Concept Drift Adaptation Methods under the Deep Learning Framework: A Literature Review

With the advent of the fourth industrial revolution, data-driven decision making has also become an integral part of decision making. At the same time, deep learning is one of the core technologies of the fourth industrial revolution that have become vital in decision making. However, in the era of epidemics and big data, the volume of data has increased dramatically while the sources have become progressively more complex, making data distribution highly susceptible to change. These situations can easily lead to concept drift, which directly affects the effectiveness of prediction models. How to cope with such complex situations and make timely and accurate decisions from multiple perspectives is a challenging research issue. To address this challenge, we summarize concept drift adaptation methods under the deep learning framework, which is beneficial to help decision makers make better decisions and analyze the causes of concept drift. First, we provide an overall introduction to concept drift, including the definition, causes, types, and process of concept drift adaptation methods under the deep learning framework. Second, we summarize concept drift adaptation methods in terms of discriminative learning, generative learning, hybrid learning, and others. For each aspect, we elaborate on the update modes, detection modes, and adaptation drift types of concept drift adaptation methods. In addition, we briefly describe the characteristics and application fields of deep learning algorithms using concept drift adaptation methods. Finally, we summarize common datasets and evaluation metrics and present future directions.

An Integrated Approach to Evaluating Eco-Innovation Strategies from the Perspective of Strategic Green Transformation: A Case of the Lithuanian Furniture Industry

Evaluation and selection of eco-innovation strategies is a significant and complex strategic decision, and despite the relevance and interest in the field of eco-innovation, the area of eco-innovation strategies has not been explored in depth in the scientific literature. Therefore, in this study, we propose an integrated approach to evaluating eco-innovation strategies from the perspective of strategic green transformation that helps decision-makers evaluate and select eco-innovation strategy aiming to achieve a competitive advantage. For this study, we adopted a validated multi-criteria decision-making methodology (MCDM) by combining Analytical Hierarchy Process (AHP) and The Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS). The reliability of the proposed framework was tested and applied in the context of the Lithuanian furniture industry. This study offers three contributions and provides a comprehensive and profound insights into eco-innovation strategies. First, this study conceptualizes eco-innovation strategy from the perspective of strategic green transformation and proposed a novel definition and classification of eco-innovation strategies leading to competitive advantage. Second, this study proposes a novel approach to the evaluation of eco-innovation strategies taking into account micro-, meso-, and macro-level environmental factors. Third, the findings of this study provide implications for scholars and decision-makers in the field of eco-innovation strategy and set an agenda for future research.

Geographic Information Systems for Facilitating Audits of the Urban Built Environment

Data collection and large-scale urban audits are challenging and can be time consuming processes. Geographic information systems can extract and combine relevant data that can be used as input to calculation tools that provide results and quantify indicators with sufficient spatial analysis to facilitate the local decision-making process for building renovations and sustainability assessment. This work presents an open-access tool that offers an automated process that can be used to audit an urban area in order to extract relevant information about the characteristics of the built environment, analyze the building characteristics to evaluate energy performance, assess the potential for the installation of photovoltaics on available building rooftops, and quantify ground permeability. A case study is also presented to demonstrate data collection and processing for an urban city block, and the relevant results are elaborated upon. The method is easily replicable and is based on open data and non-commercial tools.

A NEW FLOW-BASED MODEL OF END-TO-END INTEGRATION IN PREMIUM PRODUCT SUPPLY CHAINS

Gedryf deur die totale koste van eienaarskap, handel en tegnologiemededinging tussen die Verenigde State van Amerika en China, en die COVID-19-pandemie, ondergaan wereldwye voorsieningskettings 'n groot herstrukturering wat binnekort die besigheid en ekonomie oor die hele wereld sal transformeer. Onlangs het voorsieningskettings met end-totend-integrasie vir premium landbouvoedselprodukte as 'n nuwe sakemodel na vore gekom. Hierdie artikel ondersoek hoe hulle moet funksioneer, en identifiseer die voorsieningskettingstruktuur / - produksie / - besigheids toestande wat nodig is vir hul ontwikkeling. Ons bestudeer 'n premium voorsieningsketting wat bestaan uit baie klein plase wat piesangs van topgehalte produseer, een integreerfirma en duisende kleinhandelwinkels. Ons gebruik industrie- en besigheidsdata om 'n meervoudige roete-vloei-gebaseerde model te kalibreer van plase tot integreerder tot kleinhandelaars/markte. Ons gebruik dan sensitiwiteitsanalise om die belanghebbendes se besluitgedrag te analiseer, en identifiseer en bespreek drie hoofbesluitkwessies: kontrakboerdery, kapasiteitstrategie en besigheidsrobuustheid. Vir kontrakspesifikasie is kontraktering op prys, eerder as hoeveelheid, bevorderlik om die belange van die belanghebbendes te koördineer. Vir die kapasiteitstrategie moet die integreerder rou produkte van baie klein plase verkry eerder as minder groot plase. Vir besigheid se robuustheid kan die integreerder steeds robuuste winste verseker deur sy produkaanbod te reguleer wanneer nuwe mededingers ontstaan of vraag verander. Hierdie resultate word onder verskeie scenario's getoets om die impak van insetparameters of voorsieningskettingstruktuur te bepaal, en word geverifieer met 'n bedryfspraktisyn wat ondervinding het met veelvuldige premium agri-voedselprodukte. Die resultate, tesame met die vloeimodel en sy berekeningsprosedure, kan deur voorsieningskettingbeplanners gebruik word om nuwe besighede te begin of om kleinhandelaars se premium produkaanbiedinge in mededingende besigheidsomgewings te onderskei.Alternate :Driven by the total cost of ownership, US-China trade and technology competition, and the COVID-19 pandemic, global supply chains are undergoing a major restructuring that will soon transform business and economics all over the world. Recently, supply chains with end-to-end integration for premium agri-food products have emerged as a new business model. This paper examines how they should function, and identifies the supply chain structure/production/business conditions necessary for their development. We study a premium supply chain consisting of many small farms that produce top-quality bananas, one integrator firm, and thousands of retail stores. We use industry and business data to calibrate a multiple-route flow-based model from farms to integrator to retailers/markets. We then use sensitivity analysis to illuminate the stakeholders' decision behaviour, and identify and discuss three main decision issues: contract farming, capacity strategy, and business robustness. For contract specification, contracting on price rather than quantity is conducive to coordinating the interests of the stakeholders. For the capacity strategy, the integrator should source raw products from many small farms rather than fewer large farms. For business robustness, the integrator could still ensure robust profits by regulating its product supply when new competitors arise or demand changes. These results are tested under various scenarios to determine the impact of input parameters or supply chain structure, and are verified with an industry practitioner who has experience with multiple premium agri-food products. The results, along with the flow model and its computation procedure, could be used by supply chain planners to start new businesses or to differentiate retailers' premium product offerings in competitive business environments.

Chinese travellers' mobility decision-making processes during public health crisis situations: a Bayesian network model

Travellers' mobility decisions are fraught with uncertainty and instability during public health crises. However, existing studies have not revealed the internal mechanism of travellers' mobility changes in a public health crisis. This paper established and trained a Bayesian network model from multiple data to analyse Chinese travellers' mobility decision-making processes under COVID-19 and simulated the changes in mobility decisions in different scenarios. The results show that travellers reformulate mobility decisions in response to various information and negotiate between social customs and personal needs. Mobility can be modified through risk communication and habits adaptation. Bayesian network models provide a methodological contribution to causal exploration and scenario prediction.

Factors Influencing Physical Activity and Exercise in Older Adults during COVID-19 in South Korea

Physical activity and exercise participation among older adults have decreased dramatically because of the physical distancing measures implemented to prevent the spread of COVID-19. However, even in the face of unforeseen environmental changes, physical activity and exercise for older adults must be sustainable. This study aimed to identify the influencing physical activity and exercise participation among older adults in 2020 when varying levels of quarantine were in place as a protective measure against the COVID-19 pandemic to build a foundation for sustainable older adult health strategies. We utilized a large-scale dataset from the 2020 National Survey of Older Koreans conducted in 2020. Twenty survey questions were used as predictors, and logistic regression and decision tree analyses were utilized to identify influencing factors. Through a logistic regression analysis, 16 factors influencing exercise participation were identified. Additionally, through a decision tree analysis, 7 factors that influence exercise participation and 8 rules were derived through a combination of these factors. According to the results of this study, the use of ICT technologies, such as ‘smartphone or tablet PC', can be a useful tool to maintain or promote physical activity and exercise by older adults in a situation like the COVID-19 pandemic. In conclusion, physical activity and exercise intervention strategies should be developed with comprehensive consideration of the influencing factors to ensure that physical activity and exercise among older adults can be sustained uninterrupted in the face of unforeseen circumstances, such as the COVID-19 pandemic.

Stock Price Forecasting of IBEX35 Companies in the Petroleum, Electricity, and Gas Industries

In recent years, time series forecasting has become an essential tool for stock market analysts to make informed decisions regarding stock prices. The present research makes use of various exponential smoothing forecasting methods. These include exponential smoothing with multiplicative errors and additive trend (MAN), exponential smoothing with multiplicative errors (MNN), and simple exponential smoothing with additive errors (ANN) for the forecasting of the stock prices of six different companies in the petroleum, electricity, and gas industries that are listed in the IBEX35 index. The database employed for this research contained the IBEX35 index values and stock closing prices from 3 January 2000 to 30 December 2022. The models trained with this data were employed in order to forecast the index value and the closing prices of the stocks under study from 2 January 2023 to 24 March 2023. The results obtained confirmed that although none of the proposed models outperformed the rest for all the companies, it is possible to calculate forecasting models able to predict a 95% confidence interval about real stock closing values and where the index will be in the following three months.

Development of a Choice-framework for Covid vaccines in India using a multi-criteria decision analysis approach.

BACKGROUND: Vaccines were crucial in controlling the Covid-19 pandemic. As more vaccines receive regulatory approval, stakeholders will be faced with several options and must make an appropriate choice for themselves. We proposed a multi-criteria decision analysis (MCDA) framework to guide decision-makers in comparing vaccines for the Indian context. METHODS: We adhered to the ISPOR guidance for the MCDA process. Seven vaccine options were compared under ten criteria. Through three virtual workshops, we obtained opinions and weights from citizens, private-sector hospitals, and public health organisations. Available evidence was rescaled and incorporated into the performance matrix. The final score for each vaccine was calculated for the different groups. We performed different sensitivity analyses to assess the consistency of the rank list. RESULTS: The cost, efficacy and operational score of the vaccines had the highest weights among the stakeholders. From the six scenario groups, Janssen had the highest score in four. This was driven by the advantage of having a single dose of vaccination. In the probabilistic sensitivity analysis for the overall group, Covaxin, Janssen, and Sputnik were the first three options. The participants expressed that availability, WHO approvals and safety, among others, would be crucial when considering vaccines. CONCLUSIONS: The MCDA process has not been capitalised on in healthcare decision-making in India and LMICs. Considering the available data and stakeholder preference at the time of the study, Covaxin, Janssen, and Sputnik were preferred options. The choice framework with the dynamic performance matrix is a valuable tool that could be adapted to different population groups and extended based on increasing vaccine options and emerging evidence. *ISPOR - The Professional Society for Health Economics and Outcomes Research.

Closing the Gap Between Decision Analysis and Policy Analysts Before the Next Pandemic

Decision analysis (DA) is an explicitly prescriptive discipline that separates beliefs about uncertainties from value preferences in modeling to support decision making. Researchers have been advancing DA tools for the last 60 years to support decision makers handling complex decisions requiring subjective judgments. Recently, some DA researchers and practitioners wondered whether the difficult decisions made during the COVID-19 pandemic regarding testing, masking, closing and reopening businesses, allocating ventilators, and prioritizing vaccines would have been improved with more DA involvement. With its focus on quantifying uncertainties, value trade-offs, and risk attitudes, DA should have been a valuable tool for decision makers during the pandemic. To influence decisions, DA applications require interactions with policymakers and experts to construct formal representations of the decision frame, elicit uncertainties, and assess risk tolerances and trade-offs among competing objectives. Unfortunately, such involvement of decision analysts in the process of decision making and policy setting did not occur during much of the COVID-19 pandemic. This lack of participation may have been partly because many decision makers were unaware of when DA could be valuable in helping with the challenges of the COVID-19 pandemic. In addition, decision analysts were perhaps not sufficiently adept at inserting themselves into the policy process at critical junctures when their expertise could have been helpful.

The stratified multi criteria decision making method: An extended version

It often occurs that after a multi-criteria decision is made, the decision maker becomes unsure as to whether they have made the best decision. This doubt arises because the criteria being considered do not carry the same weightings. This instability is relevant to the consideration of possible future events, such as a possible recession following the COVID-19 outbreak, which may affect the criteria weightings. The stratified multi-criteria decision-making method (SMCDM) has been proposed to address this issue. This method suggests the consideration of a number of states in the decision-making process. In each state, the weightings of the criteria are different depending on which event or which combination of events are being considered. The states are associated with transition probabilities that are used to compute the optimal weightings of the criteria. This paper suggests approaches to compute the transition probabilities. Moreover, the consideration of several events in SMCDM results in a great number of states and this would be a time consuming and error prone process. Hence, the incremental enlargement characteristic of the concept of stratification (CST) is added to SMCDM in order to reduce the large numbers of states to a manageable quantity. IEEE

Multi-Criteria Decision-Making with Novel Pythagorean Fuzzy Aggregation Operators

Unpredictability and fuzziness coexist in decision-making analysis due to the complexity of the decision-making environment. "Pythagorean fuzzy numbers” (PFNs) outperform "intuitionistic fuzzy numbers” (IFNs) when dealing with unclear data. The "Pythagorean fuzzy set” (PFS) is a useful tool because it removes the restriction that the sum of membership degrees be less than or equal to one by substituting the square sum for the sum of membership degrees. This study proposes two aggregating operators (AOs). The recommended operators outperform the already specified PFN operators. The proposed operator is utilised in the multicriteria decision-making process to identify the best candidate for instruction (MCDM).

Knowledge Discovery to Support WTI Crude Oil Price Risk Management

The high volatility of commodity prices and various problems that the energy sector has to deal with in the era of COVID-19 have significantly increased the risk of oil price changes. These changes are of the main concern of companies for which oil is the main input in the production process, and therefore oil price determines the production costs. The main goal of this paper is to discover decision rules for a buyer of American WTI (West Texas Intermediate) crude oil call options. The presented research uses factors characterizing the option price, such as implied volatility and option sensitivity factors (delta, gamma, vega, and theta, known as "Greeks”). The performed analysis covers the years 2008–2022 and options with an exercise period up to three months. The decision rules are discovered using association analysis and are evaluated in terms of the three investment efficiency indicators: total payoff, average payoff, and return on investment. The results show the existence of certain ranges of the analyzed parameters for which the mentioned efficiency indicators reached particularly high values. The relationships discovered and recorded in the form of decision rules can be effectively used or adapted by practitioners to support their decisions in oil price risk management.

Analyzing Student Evaluations of Teaching in a Completely Online Environment

Almost all educational institutions have shifted their academic activities to digital platforms due to the recent COVID-19 epidemic. Because of this, it is very important to assess how well teachers are performing with this new way of online teaching. Educational Data Mining (EDM) is a new field that emerged from using data mining techniques to analyze educational data and making decision based on findings. EDM can be utilized to gain better understanding about students and their learning processes, assist teachers do their academic tasks, and make judgments about how to manage educational system. The primary objective of this study is to uncover the key factors that influence the quality of teaching in a virtual classroom environment. Data is gathered from the students' evaluation of teaching from computer science students of three online semesters at X University. In total, 27622 students participated in these survey. Weka, sentimental analysis, and word cloud generator are applied in the process of carrying out the research. The decision tree classifies the factors affecting the performance of the teachers, and we find that student-faculty relation is the most prominent factor for improving the teaching quality. The sentimental analysis reveals that around 78% of opinions are positive and "good” is the most frequently used word in the opinions. If the education system is moved online in the future, this research will help figure out what needs to be changed to improve teachers' overall performance and the quality of their teaching.

Using MCDA to assist an Intermunicipal community develop a resilience strategy in face of the pandemic caused by the SARS-CoV-2.

The topic of regional economic resilience has been the subject of intense debate in the academic and political fields over the past decade and gained a new sense of urgency because of the pandemic caused by the SARS-CoV-2 virus as territories faced relevant impacts on their economies and social structures. The economic downturn, the increase in unemployment, and the deterioration of social conditions lead policy makers to search for solutions to make their territories more resilient to this type of event. The current article discusses how multicriteria decision analysis (MCDA) was used to help a Portuguese Intermunicipal Community, formed by 16 councils, develop a strategy to make its territory more cohesive, competitive, sustainable, and resilient. In addition to discussing an innovative application of a MCDA technique, this article illustrates how, through a MCDA approach, it was possible to reach a consensus among several policymakers, despite each of them having their own political agendas.

Technological, healthcare and consumer funds efficiency: influence of COVID-19

This paper aims to analyze the efficiency of the funds in technological, healthcare, and consumer cyclical sectors based on the U.S. News & World Report rankings. We employed a Principal Component Analysis to select the indicators to explain efficiency. Then, we have used an alternative approach that combines Data Envelopment Analysis (DEA) with Multiple Criteria Decision Aiding, the Value-Based DEA, to assess the efficiency of funds for 1 year (2020), 3 years (2018–2020), and 5 years (2016–2020). The results highlight that in 2020 the number of efficient funds is much smaller than in previous periods and this can be justified by the effect of the COVID-19 pandemic crisis. The sectors with the most efficient funds are technology and healthcare. The factors that determine the efficiency of funds in the health sector and the technology sector are quite different, although they have not undergone major changes in the three periods considered. For managers, health funds are seen as low risk and hardly consider the return factors in all analyzed periods, which is often considered as benchmarks for inefficient funds. In the technology sector, Beta and Alpha are generally the indicators with the greatest weight in fund efficiency, showing that these funds beat the market in terms of returns and are less risky than the benchmark. This study seeks to complete the scarce existing literature on the subject, namely in the sectors under analysis, seeking to identify the indicators that fund managers ponder most to consider a fund as efficient. As far as we know, the joint efficiency analysis of these sectors and the impact they suffered from the COVID-19 pandemic are new in the literature.

A Novel Statistical and Neural Network Combined Approach for the Cloud Spot Market

The price of virtual machine instances in the Amazon EC2 spot model is often much lower than in the on-demand counterpart. However, this price reduction comes with a decrease in the availability guarantees. Several mechanisms have been proposed to analyze the spot model in the last years, employing different strategies. To our knowledge, there is no work that accurately captures the trade-off between spot price and availability, for short term analysis, and does long term analysis for spot price tendencies, in favor of user decision making. In this work, we propose (a) a utility-based strategy, that balances cost and availability of spot instances and is targeted to short-term analysis, and (b) a LSTM (Long Short Term Memory) neural network framework for long term spot price tendency analysis. Our experiments show that, for r4.2xlarge, 90 percent of spot bid suggestions ensured at least 5.73 hours of availability in the second quarter of 2020, with a bid price of approximately 38 percent of the on-demand price. The LSTM experiments were able to predict spot prices tendencies for several instance types with very low error. Our LSTM framework predicted an average value of 0.19 USD/hour for the r5.2xlarge instance type (Mean Squared Error [Formula Omitted]) for a 7-day period of time, which is about 37 percent of the on-demand price. Finally, we used our combined mechanism on an application that compares thousands of SARS-CoV-2 DNA sequences and show that our approach is able to provide good choices of instances, with low bids and very good availability.

Policy Analysis of Low-Carbon Energy Transition in Senegal Using a Multi-Criteria Decision Approach Based on Principal Component Analysis

Senegal has been investing in the development of its energy sector for decades. By using a novel multi-criteria decision analysis (MCDA) based on the principal component analysis (PCA) method, this paper develops an approach to determine the effectiveness of Senegal's policies in supporting low-carbon development. This was determined using six criteria (C1 to C6) and 17 policies selected from the review of Senegal's energy system. In order to determine the optimal weighting of the six criteria, a PCA is performed. In our approach, the best weighted factor is the normalized version of the best linear combination of the initial criteria with the maximum summarized information. Proper weighted factors are determined through the percentage of the information provided by the six criteria kept by the principal components. The percentage of information is statistically a fit of goodness of a principal component. The higher it is, the more statistically important the corresponding principal component is. Among the six principal components obtained, the first principal component (comp1) best summarizes the values of criteria C1 to C6 for each policy. It contains 81.15% of the information on energy policies presented by the six criteria and was used to rank the policies. Future research should take into account that when the number of criteria is high, the share of information explained by the first principal component could be lower (less than 50% of the total variance). In this case, the use of a single principal component would be detrimental to the analysis. For such cases, we recommend a higher dimensional visualization (using two or three components), or a new PCA should be performed on the principal components. This approach presented in our study can serve as an important benchmark for energy projects and policy evaluation.

Comparative Analysis of Pitch Ratings in All Formats of Cricket

The article identifies measurable attributes to find the consistency in pitch ratings which are otherwise subjective decisions made by referees for international test match cricket. To do so, the article uses statistics related to test matches, one-days and T20s played among all test playing nations between March 2017 and March 2019 (53 tests, 142 T20s and 172 one-day matches: the next two seasons ending May 2020/2021 were hit by COVID-19 and hence excluded). To measure the consistency of pitch ratings (very good, good, above average, average, below average and poor), measurable attributes like runs/day, wickets/day, runs/over, runs/wicket and overs/wicket were identified. To rank pitch ratings using these attributes, the multi-criteria decision-making technique—PROMETHEE II was used. We found that the referee pitch ratings are largely consistent and the attributes developed can be utilized to further analyse future judgements regarding pitch ratings. Further, six-pitch ratings can be clustered into two distinct groups that are significantly different from each other. The article is among the first to analyse sports pitch ratings by using team performance-based statistics. This study paves the way for similar studies and development of newer statistical flow-based attributes. © 2023 XLRI Jamshedpur, School of Business Management & Human Resources.

Informative initiatives as a useful tool to raise awareness of food waste. An application to higher education

PurposeBecause food waste is a serious problem today, society is currently aiming for more responsible consumption to minimize it, as defined in the 12th goal of the United Nations Sustainable Development Goals. This study aims to examine whether an informative initiative can help to raise university students' awareness of food waste consequences.Design/methodology/approachThe initiative consisted of explaining the problem of food waste to students of two marketing subject modules within economics and business administration degrees and asking them to participate in an activity in which they analyzed their own behavior. To assess its impact, two questionnaires about the students' food waste behaviors were administered, before and after the initiative, adopting an experimental design.FindingsThe results show that the information and awareness activities were successful, because, after the initiative, the students were more aware about the food waste problem and its consequences and were more critical of their behavior regarding the management of leftovers at home.Research limitations/implicationsDespite some circumstances under which the study was conducted (the COVID-19 pandemic and the lockdown), the practical and social implications are relevant.Practical implicationsThis study offers some interesting practical implications for educational institutions that want to inform and train students in more responsible consumption behavior. It shows that an initiative in which students are involved, like collecting data about food waste, in their homes with a diary, and informative sessions can be useful to increase students' awareness of food waste to behave in a more sustainable way.Social implicationsThese findings may be of interest to academics for designing initiatives that try to train and educate young people in making more responsible personal and professional decisions.Originality/valueThis study analyzes the impact of an awareness-raising initiative about food waste in higher education, which is a relatively neglected topic in the literature.

Understanding the E-Banking Channel Selection Behavior of Elderly Customers: A Small-World Network Perspective

To reveal the influence mechanism of e-banking channel selection of elderly customers, according to the analysis of elderly customers'decision-making process, a threshold model is proposed by using small world customer relationship network and variable setting in this study. The multi-agent simulation of e-banking channel selection behavior of elderly customers is carried out from the perspectives of channel diffusion speed and customer channel selection proportion in the context of Covid-19 pandemic. The research shows that channel performance and individual differences of customers affect the adoption of e-banking by elderly customers. This study also has found that network size and network density can regulate the impact of channel performance on the selection behavior of elderly groups. However, they could play a regulatory role under certain conditions. Finally, this study puts forward some suggestions to improve the channel diffusion efficiency, such as building an elderly friendly e-financial service channel and construction of elderly business market culture.