The transformation of software development from monolithic frameworks to microservices-based architectures, focusing on the challenges of creating a unified defect prediction model that spans various programming languages in practice of automating integration of code modification into a single codebase. It proposes a hybrid machine learning approach to enhance defect prediction accuracy by integrating different data sources and algorithms. The goal is to create a language and project-independent model. The hybrid model combines Bi-Directional LSTM (BiD-LSTM) networks and Attention mechanisms, static code metrics, and BERT-based language models. BiLSTM-Attention captures temporal dependencies within Abstract Syntax Trees (ASTs), static code metrics provide insights into software complexity, and BERT interprets textual context for a holistic understanding of code snippets. The research methodology involves quantitative techniques, starting with a literature review to establish the theoretical foundation. An empirical study follows, encompassing data gathering, feature crafting and pre-processing, model building, training and evaluation, validation and analysis and conclusions. The research’s insights aim to improve defect prediction techniques, contributing to software engineering’s pursuit of better quality and reliability.

Credit risk assessment is a very crucial task for every firm. Especially, companies which give goods or services to their customers to be paid back on a later date or gives loans need to have an efficient credit risk assessment system to avoid financial losses. For accurate assessment of credit risk, precise credit scoring models are needed which the firms may use as a decision-support tool for making lending decisions. Approving credit to bad customers or denying credit to potential customers both can incur profit losses for the firm. Several researchers have addressed this credit risk assessment problem previously by building credit scoring models using various machine learning algorithms. But the performance of these models gets affected due to the skewed nature of the credit scoring data and the hidden correlations between the data features. It has been noted from literature that the credit scoring models are sensitive to the highly imbalanced class ratio which exists in credit scoring datasets. We address these challenges in this paper by proposing a deep-Q network based reinforcement learning model. The model uses two reward functions to help the model learn the optimal policy of detecting bad customers and maintain a balance between the credit approval and decline rate. We have then compared our DQN model performance with other classification models for the same dataset to demonstrate the effective utility of our model in improving the effective lending decisions.

We propose a novel method to analyze clickstream data that can assist E-commerce retailers with marketing precision based on a better understanding of customer intentions. Design/Methodology/approach - Multiple approaches have been used with real word data from an electronic online retailer's clickstream data. This database contains 1,921,451 data from July 2019 to March 2020 from an electronic e-commerce retailer in Taiwan. In our approach, we cluster clickstream data with the K-means model and then apply the Decision tree model to identify a pattern in each cluster. On Mapping these clusters, we further analyzed that each cluster could map to the pre-purchase and purchase of customer journey model. Findings - We find a novel approach of using each session of browsing behavior as one unit to prevent a situation in which a customer may have different intentions during different periods. Furthermore, this study mainly focuses on browsing time in each category to analyze customers' preferences. Nevertheless, the results show it is a feasible approach, and one can explore customers' intentions from a new perspective. This study provides a new customer browsing intention's analyzing mode of integrating theory and practice by clickstream data, which can be applied to business. Research Limitations/Implications - Our research is limited to the browsing time in each category. One way to improve precision and accuracy would be to add other attributes to the model, such as browsing paths. Another is clickstream data cannot map retention and advocacy of customer journey. Originality/Value - We overcame the limitation of previous research, which focused on the customer journey, by taking one customer's all consumer behavior as one unit. In our study, we use each session of browsing behavior as one unit to prevent a situation in which a customer may have different intentions during different periods.

This study aims to investigate the constraints faced by the rural community in the Hadoti region of Rajasthan, India, regarding the implementation of the Swachh Bharat Mission (Clean India Mission).The Swachh Bharat Mission was launched in 2014 with the objective of achieving universal sanitation and cleanliness across the country.However, the effectiveness of its implementation in rural areas, particularly in the Hadoti region, has been influenced by various constraints.The study identifies key obstacles including inadequate infrastructure, limited access to sanitation facilities, cultural and social norms, financial constraints, and inadequate awareness and education.The research utilized a mixed-methods approach, combining quantitative surveys and qualitative interviews, to gather data from a representative sample of rural households in the Hadoti region.The study identified several key constraints that hinder the successful implementation of the Swachh Bharat Mission.The study found that the majority of the farmers were under constraints faced through the personal problems section most of the respondents answered with Lack of information (53.44%),Under constraints faced through social problems section most of respondents answered with Change in people's mindset or behavior (57.19%) and Under constraints faced through administrative problems, the respondent's data was mostly received in the lack of encouragement (42.50%).The study also revealed that the farming community of the research area faced various challenges including low education level, insufficient agricultural resources and lack of knowledge of new technology etc. HIgHlIgHTSm The highest result found under Lack of information 171 (53.44%) respondents.m The highest result under Change in people's mindset or behavior 183 (57.19%) respondents.m Among the administrative problems analyzed, Lack of encouragement scored highest in segment 136 (42.50%) respondents.

Purpose Explainable artificial intelligence (XAI) has importance in several industrial applications. The study aims to provide a comparison of two important methods used for explainable AI algorithms. Design/methodology/approach In this study multiple criteria has been used to compare between explainable Ranked Area Integrals (xRAI) and integrated gradient (IG) methods for the explainability of AI algorithms, based on a multimethod phase-wise analysis research design. Findings The theoretical part includes the comparison of frameworks of two methods. In contrast, the methods have been compared across five dimensions like functional, operational, usability, safety and validation, from a practical point of view. Research limitations/implications A comparison has been made by combining criteria from theoretical and practical points of view, which demonstrates tradeoffs in terms of choices for the user. Originality/value Our results show that the xRAI method performs better from a theoretical point of view. However, the IG method shows a good result with both model accuracy and prediction quality.

Abstract: In order to forecast anomalies more correctly, a moderately excellent network detection system for intrusions requires a high rate of detection and a relatively low false alarm rate. Because older datasets cannot capture the design of a set of recent attacks, modeling on the basis of these datasets lacks generalizability. We discuss numerous models before concluding with the one that performs best utilizing various types of evaluation measures. Along with modeling, a detailed data analysis on the properties of the set of data itself is performed for a more complete picture employing our comprehension of a correlation variance, and similar aspects. Furthermore, hypothetical considerations for potential network intrusion detection systems are presented, including advice on prospective modeling and dataset production.

Food Industries, at this moment, are moving towards a new phase, and this phase will be governed by consumers and not by the industry leaders. The report shows that claims on sustainability, health, wellness, and transparency would govern the future trends in the food industry. Currently, there are several cases of misleading and false claims which hamper consumer trust. So, to uphold consumer trust, authentication of claims through transparency in the food supply chain is required, and blockchain technology can bring transparency at relatively low transaction costs. Once in a blockchain network, data is very difficult to manipulate, with no single point of authority to mess and collapse the system. Though we see mostly the financial systems using blockchain's decentralized functionality, there is a growing trend of innovative applications being built in the supply chain area for contracts and operations. With effort in the right direction and over time, blockchain will recast how operations and processes are done across the industry, including public sectors. The paper reviews the opportunity for the blockchain in enabling food industries for future-readiness, empowering the consumers in verifying the product claims and thus prevent themselves from food fraud. In doing so, the paper considers the future trends in the food industry, identifies current food fraud cases, and outlines the various applications in the agri-food chain and challenges associated with it.

One of the core challenges in digital marketing is that the business conditions continuously change, which impacts the reception of campaigns. A winning campaign strategy can become unfavored over time, while an old strategy can gain new traction. In data driven digital marketing and web analytics, A/B testing is the prevalent method of comparing digital campaigns, choosing the winning ad, and deciding targeting strategy. A/B testing is suitable when testing variations on similar solutions and having one or more metrics that are clear indicators of success or failure. However, when faced with a complex problem or working on future topics, A/B testing fails to deliver and achieving long-term impact from experimentation is demanding and resource intensive. This study proposes a reinforcement learning based model and demonstrates its application to digital marketing campaigns. We argue and validate with actual-world data that reinforcement learning can help overcome some of the critical challenges that A/B testing, and popular Machine Learning methods currently used in digital marketing campaigns face. We demonstrate the effectiveness of the proposed technique on real actual data for a digital marketing campaign collected from a firm.

Data availability and accessibility have brought in unseen changes in the finance systems and new theoretical and computational challenges. For example, in contrast to classical stochastic control theory and other analytical approaches for solving financial decision-making problems that rely heavily on model assumptions, new developments from reinforcement learning (RL) can make full use of a large amount of financial data with fewer model assumptions and improve decisions in complex economic environments. This paper reviews the developments and use of Deep Learning(DL), RL, and Deep Reinforcement Learning (DRL)methods in information-based decision-making in financial industries. Therefore, it is necessary to understand the variety of learning methods, related terminology, and their applicability in the financial field. First, we introduce Markov decision processes, followed by Various algorithms focusing on value and policy-based methods that do not require any model assumptions. Next, connections are made with neural networks to extend the framework to encompass deep RL algorithms. Finally, the paper concludes by discussing the application of these RL and DRL algorithms in various decision-making problems in finance, including optimal execution, portfolio optimization, option pricing, hedging, and market-making. The survey results indicate that RL and DRL can provide better performance and higher efficiency than traditional algorithms while facing real economic problems in risk parameters and ever-increasing uncertainties. Moreover, it offers academics and practitioners insight and direction on the state-of-the-art application of deep learning models in finance.

Detecting anomalies in their internal processes can be indicators for fraud and inefficiencies at Firms. However, classic anomaly detection is not very frequently researched. In this paper, we propose a combination of clustering and time series analysis to detect and analyze anomalies occurring in executing a business process. Our approach does not rely on any prior knowledge about the process and can be trained on a noisy dataset already containing the anomalies. We demonstrate its effectiveness by evaluating it on 300Â different datasets and testing its performance against rule-based state-of-the-art anomaly detection methods. Our approach clustered vendors precisely and showed anomalies not shown by rule-based systems. Furthermore, our approach can analyze the detected anomalies in terms of which month within the year causes the anomaly, identifying the root cause.

The Internet of Things (IoT) has changed the way we think about food. Farmers are looking to predictive technology to mitigate risk and weather while maximizing their yield. Consumers can have the option of having their favorite brands and ingredients delivered right to their door. All of this without inflating delivery costs. This has resulted in a massive growth in research interest in the IoT at both academics and industrialists to develop and deploy IoT-based applications for transparency and efficiency within the food sector. This chapter focuses on utilizing IoT and similar technologies in the food supply chain (FSC), specifically in farm to folk. It presents IoT applications that have been successfully developed and deployed in FSCs, the pros and cons of IoT implementation. Finally, it describes future trends such as elements of Industry 4.0, blockchain, intelligent packaging, and artificial intelligence.

The impact of price and price changes should not be ignored while designing algorithms for predicting customer choice. Consumer preferences should be modeled with consideration of price effects. Businesses need to consider for efficient prediction of an individual's purchase behaviour. Personalized recommendation systems have been studied with machine learning algorithms. However, the price-aware personalized recommendation has received little attention. In this paper, we attempt to capture insightful economic results considered in the marketing and economics disciplines by employing modern machine learning architecture for predicting customer choice in a large-scale supermarket context. We extract personalized price sensitivities and examine their importance in consumer behaviour. The employed data collected from a supermarket chain in Germany consists of implicit feedback based on customer-product interactions and the price of every interaction. We propose a two-pathway matrix factorization (2way-MF) model that is price-aware and tries to memorize customer-product interaction's implicit feedback. The proposed models achieve better model performance than standard Matrix Factorization models widely used in the industry. The approach was re-validated with data from supermarket chain in Taiwan. Other industries can adopt the proposed framework of modeling customer's preferences based on price sensitivity. We suggest that further research and analyses could help understand the cross-price elasticities.

It does not need to be mentioned that Business cards are essential for businesses and consumers alike across all industries irrespective of size of the business. Today, these cards not only help in giving contact details but building a brand. In digital era the business card is also going through the journey of digital transformation. While some of the expectation from such electronic business card can be articulated as - Easy to share, cost-effective, Eco-friendly, Easy to customize, store the information conveniently and contact management While taking a closer look at these expectation the authors were convinced that such system should be based on a cloud architecture .The authors with their experience on the 2P-cloud Architecture realized that the concept can be extended for cloud services 4-tier architectures and an Electronic Business card system can be built on it. In this study, we proposal an instance of the cloud electronic business card (EBC) generation framework which is according to the Key point of view of Business models, Operational processes and User experiences of Digital transformation studied by Abhijit et al. and the five skills and competencies of CDO studied by Anna et al. and the 2P-Cloud architecture studied by Chuang et al as main. In this study, we focused on the system availability of cloud EBC system in the development processes, which is to attend the smooth process of Human-Computer Interaction when we design an IT system.

The concept of cross project and within project software prediction is an important approach that is used to analyze the defects of software. The different scenario is used to analyze the functions of software prediction with the help of NLP Techniques. Defects are widespread in software systems and can cause a variety of problems for software users. The process software technology of predicting the defects are used to include different software components that helps in analyzing the functions of cross projects. There is a wide range of circumstances in the approach of suitable functions. It identifies the possibility of the system on the basis of different assurance of software prediction. The given article helps in analyzing the process of NLP techniques for the prediction of software. The different aspects are used to evaluate the framework which requires functions of cross projects.