Millions Of Customers Research Articles

Comprehensive review of machine learning models for sql injection detection in e-commerce

With the steady expansion of online commerce, e-commerce sites have become increasingly attractive targets for hackers. These sites serve millions of customers and often hold valuable, confidential, and sometimes financial information in their databases. One particularly dangerous type of attack is SQL injection, which exploits vulnerabilities in web applications to influence backend databases, posing significant threats to such platforms. Traditional defenses like desktop firewalls, input validation, and parameterized queries provide some level of protection but are often insufficient against newer injection variations and sophisticated attackers. The utilization of machine learning to enhance cybersecurity against more advanced threats has been demonstrated as a promising approach. This systematic review examines how various machine learning algorithms are applied to detect SQL injection attacks that could potentially harm e-commerce systems. By identifying and analyzing the relevant literature, this review highlights the effectiveness of different algorithms and their practical applications in enhancing the security of online commerce platforms. More specifically, five techniques were assessed on both real and synthetic datasets: Logistic Regression, Naive Bayes, Random Forest, Artificial Neural Network, and two combined models (Logistic Regression & Naive Bayes, and Artificial Neural Network & Random Forest). The findings indicate that Random Forest performed better than other algorithms in the decision tree family, attributed to its ability to balance precision and recall effectively. However, limitations such as using a single dataset and the computational complexity of some models were noted. This review provides insights for practitioners on selecting appropriate detection models and outlines approaches to address current limitations through future work. Addressing these limitations could involve using more diverse datasets, optimizing computational efficiency, and exploring advanced ensemble methods and neural network architectures.

Evaluating intrusion detection for microservice applications: Benchmark, dataset, and case studies

Microservices are predominant for cloud-based applications, which serve millions of customers daily, that commonly run business-critical systems on software containers and multi-tenant environments; so, it is of utmost importance to secure these systems. Intrusion detection is a widely applied technique that is now being used in microservices to build behavior detection models and report possible attacks during runtime. However, it is cumbersome to evaluate and compare the effectiveness of different approaches. Standardized frameworks are non-existent and without fairly comparing new techniques to the state-of-the-art, it is difficult to understand their pros and cons. This paper presents a comprehensive approach to evaluate and compare different intrusion detection approaches for microservice applications. A benchmarking methodology is proposed to allow users to standardize the process for a representative and reproducible evaluation. We also present a dataset that applies representative workloads and technologies based on microservice applications state-of-the-art. The benchmark and dataset are used in three case studies, characterized by dynamicity, scalability, and continuous delivery, to evaluate and compare state-of-the-art algorithms with the objective of tackling intrusion detection in microservices. Experiments show the usefulness and wide application range of the benchmark while showing the capacity of intrusion detection algorithms in different applications and deployments.

Capacitated vertiport and charging station location-allocation problem for air taxi operations with battery and fleet dispatching considerations: a case study of New York city

Set to begin operations in the coming years, air taxi is an emerging ride-sharing aviation service that plans to commute millions of customers in metropolitan cities every day. However, existing literature has not holistically investigated the impact of the various strategic, tactical, and operations decisions pertaining to air taxi services (ATS). This research adopts a simulation-based framework to address the capacitated infrastructure location and demand allocation problems associated with ATS. Specifically, we determine the following decisions: (i) location and size of operating facilities and charging stations (strategic), (ii) air taxi fleet required to serve the expected demand at a specified service level (strategic), (iii) threshold minimum charge required for efficient air taxi operations (tactical), and (iv) real-time allocation of customer demand (operational). The proposed approach identifies the infrastructure locations using a clustering algorithm, and subsequently addresses the capacitated location-allocation problem for ATS by employing a simulation-based model. To test the effectiveness of the proposed approach, we consider a case study of New York City. We leverage the estimated air taxi demand and evaluate the proposed model by considering the weighted sum of fleet utilization and customer waiting time.

The Effect of Entrepreneurship Education on Micro-entrepreneurial Outcomes Funded by MFIs

Microfinance institutions (MFIs) are widely catering to millions of customers deprived of mainstream lending services. Beyond doubt, they are fulfilling their goal of loan provision to the deprived creating an opportunity for them to better their lives. Herein, arises a critical question, whether loan is enough to achieve the primary purpose of this very loan, which is the upliftment of the borrower, or more than funding is needed? Deep investigation is deemed to explore an answer to this. In this process, this paper compares the performance of micro-entrepreneurs who undergo and who do not undergo entrepreneurial training and education programs. Thus, establishing the impact of entrepreneurial training and education programs on micro-enterprises. This scientific research provides discreet insight for researchers to narrow in on related significant research topics and presents the organizations an opportunity to decide the thrust they want to apply on entrepreneurial training and education programs being in a position to evaluate the long-term impact of their approach and investment. It is a longitudinal study performed on the 121 MFI clients of 4 microfinance institutions in 2 different states (Bihar and Orrisa) of India. All the clients have taken loan with the purpose of starting micro-enterprise. 61 received entrepreneurial education provided by MFIs and rest have started without any entrepreneurial education. Every year from 2015 to 2021, semi-structured, in-depth telephonic interviews were performed to track, measure, and analyze respondents' transition from loan disbursement to entrepreneurship. Though, all the beneficiaries do not find the education programs in absolute synchronisation with their development needs in terms of skills and knowledge, still the results of those who have attended such programs are found to be better than those who haven’t. Also, the majority of them appear content with the results of their entrepreneurship education and are performing better in comparison to those who have not undergone it. The results advocate that effective education should be provided on entrepreneurial, social, health and family aspects by each MFI to achieve the basic purpose of its existence. The study provides valuable insights for the stakeholders involved in developing micro-enterprises.

LIC: MEASURING THE EFFECTIVENESS OF INTERNET ADVERTISEMENTS

The Insurance sector is an essential part of the economy because it helps people and businesses reduce risk and protect their finances. It functions by obtaining premium payments from policyholders and providing reimbursement for specific losses, such as injuries, diseases, or property damage. It is vital for insurers to adapt and innovate in order to remain competitive and satisfy the changing demands of the market since the industry continuously changes due to advancements in technology, data analytics, and changing customer preferences. One of Indias biggest and oldest life insurance firms, the Life Insurance Corporation of India (LIC), was founded in 1956. It is a significant player in the Indian insurance industry and a state-owned organization. LIC serves millions of customers by offering a variety of life insurance and investment products. Given that it is owned by the government, it plays a crucial role in encouraging long-term savings and financial inclusion in India. This article examines the profound influence of internet advertising on the Life Insurance Corporation of India (LIC). As digitalization continues to reshape the business landscape, LIC has embarked on a strategic journey to harness the potential of online advertising. The study investigates the multifaceted impact of internet advertising on LIC, encompassing heightened brand visibility, targeted customer engagement, and operational efficiency. By leveraging data-driven insights and innovative marketing strategies, LIC is not only expanding its market reach but also fostering stronger customer relationships in the digital era. This abstract offers a glimpse into how internet advertising is reshaping LIC and 39;s strategies and its pivotal role in securing the corporations relevance and competitiveness in the contemporary insurance industry. KEYWORDS: Internet advertising, LIC insurance services, online marketing, advertising campaigns.

Subseasonal to seasonal streamflow forecasting in a semiarid watershed

AbstractOperational streamflow forecasting is critically important to managers of river basins that supply water, hydropower, and flood protection. While seasonal water supply forecasts (WSFs) are important for long‐term water resources planning operations, shorter term (e.g., 1–5 weeks) streamflow forecasts are critical for balancing water conservation with flood risk during wet periods. In this study, we designed a streamflow forecasting system with the water resources group at the Salt River Project (SRP), a provider of water and power to millions of customers in central Arizona (AZ), to provide streamflow forecasts for a diverse and operationally important set of watersheds in AZ. The forecast system uses machine learning to make seasonal WSFs, a rainfall–runoff model driven by ensemble meteorological forecasts to make 35‐day streamflow forecasts, and an innovative approach to improve the WSFs based on the 35‐day streamflow forecasts. This model integration allows for an assessment of the impact of different meteorological forecasts on WSFs, helping SRP to balance water conservation goals with shorter term flood risks. In addition, seasonal WSFs are improved in the early winter when they incorporate the 35‐day streamflow predictions. Furthermore, these improvements are larger than when they incorporate 7‐day streamflow predictions, demonstrating the value of using subseasonal to seasonal (S2S, >1–2 weeks) forecasts to improve seasonal WSFs in these watersheds.

The Value of Personal Data in Internet Commerce: A High-Stakes Field Experiment on Data Regulation Policy

Personal data have become a key input in internet commerce, facilitating the matching between millions of customers and merchants. Recent data regulations in China, Europe, and the United States restrict internet platforms’ ability to collect and use personal data for personalized recommendation and may fundamentally impact internet commerce. In collaboration with the largest e-commerce platform in China, we conduct a large-scale field experiment to measure the potential impact of data regulation policy and to understand the value of personal data in internet commerce. For a random subset of 555,800 customers on the Alibaba platform, we simulate the regulation by banning the use of personal data in the home page recommendation algorithm and record the matching process and outcomes between these customers and merchants. Compared with the control group with personal data, we observe a significantly higher concentration in the algorithmic recommendation of products in the treatment group and a very sharp decrease in the matching outcomes as measured by both customer engagement (click-through rate and product browsing) and market transaction (sales volume and amount). The negative effect is disproportionate and more pronounced for niche merchants and customers who would benefit more from e-commerce. We discuss the potential economic impact of data regulation on internet commerce as well as the role of personal data in generating value and fostering long-tail innovations. This paper was accepted by Chris Forman, information system. Funding: Z. Yuan wants to acknowledge financial support from NSFC [Grants 72203202, 72192803 and 72141305]. Supplemental Material: The data files and online appendix are available at https://doi.org/10.1287/mnsc.2023.4828 .

Implementing the Customer-Centric Mandate: Journey management from the perspective of large organisations

The film Everything Everywhere All at Once was 2022’s runaway hit, winning praise for blending characters, genres and timelines. To some, it made perfect sense – to others, it was chaos. I saw in it a parallel to the environment in which in-house customer experience (CX) teams operate, especially in large organisations with millions of customers and thousands of employees. With multiple user segments, business goals, time horizons and journeys – it’s everything, everywhere, all at once!

Business Strategy Analysis in Retail Economy: A Case Study of 7-Eleven

With the rapid development of society, the retail industry is threatened by big shopping malls and online shops. This article investigates the secret of 7-Eleven's success under threat through books and online research. The study found that 7-Eleven has actively responded to the changing times and continuously made innovations. 7-Eleven has created an intensive site selection strategy which significantly improved selling efficiency. 7-Eleven also convinced the suppliers to continue working during holiday, which keeps 7-Eleven’s products fresh all the time. In addition to that, 7-Eleven also developed a new delivery pattern that reduce the need of delivery trucks. While 7-Eleven pay much attention on maintaining various of products, it also creates own products, which attract millions of customers. Through analyzing 7-Eleven’s business wisdom, this article gives the retail industry ideas about how to survive and success in the rapidly developing society.

The Alibaba Challenge: How to Effectively Engage with a Billion Customers

Alibaba conducts millions of transactions involving billions of dollars each year. Yitong Wang, Ofer Mintz, Depin Chen, and Kehan Chen describe how the company uses AI-powered chatbots to complement its human resources so as to maximize engagement with its millions of customers and with its vendors.

BIG DATA ANALYTICS IN SPOTIFY

Millions of customers daily enjoy and use the popular music streaming service Spotify. The app is the biggest on-demand music service in the world and is extremely popular in the music industry. The most popular music streaming software, Spotify, is made possible by cutting-edge technology like Big Data. With a current net value of over $25 billion, Spotify significantly influences the music business by utilizing data in novel ways. Keywords: Data management system, data analytics, music streaming, data service

Influence of Hotel Ambience and Performance of Hotels in Uganda. A Critical Literature Review

Purpose: Globally, there are over 160,000 star rated hotels with more than 14 million accommodation (rooms) available to millions of customers across low, middle and upmarket hotels. The overall objective of this study was to examine influence of hotel ambience and performance of hotels in upmarket areas.
 Methodology: The paper used a desk study review methodology where relevant empirical literature was reviewed to identify main themes and to extract knowledge gaps.
 Findings: The study concluded that upmarket hotel managers should improve and maintain consistency in service quality to enhance accommodation performance of their hotels. Upmarket hotel managers should place considerable importance on improving the levels of service reliability/trustworthiness, service reputation/credibility, and service recovery when something goes wrong, service accessibility/flexibility, service professionalism/skills and service behaviour/attitude in their daily operations. Upmarket hotel managers pay more attention to service quality delivery for better room efficiency and customer satisfaction.
 Unique Contribution to Theory, Policy and Practice: This study recommended that that the hotel regulatory authorities should improve on regulations and control of accommodation facilities to facilitate better accommodation performance of upmarket hotels. Upmarket hotel managers should consistently improve the quality of room facilities and service quality as well as support regulatory control to cause positive and significant changes in accommodation performance of upmarket hotels. The customers should use hotel star rating status as guide in comparing and making decisions on choice of accommodation facilities of upmarket hotels.

The 2021 Texas Power Crisis: distribution, duration, and disparities.

Precipitated by an unusual winter storm, the 2021 Texas Power Crisis lasted February 10 to 27 leaving millions of customers without power. Such large-scale outages can have severe health consequences, especially among vulnerable subpopulations such as those reliant on electricity to power medical equipment, but limited studies have evaluated sociodemographic disparities associated with outages. To characterize the 2021 Texas Power Crisis in relation to distribution, duration, preparedness, and issues of environmental justice. We used hourly Texas-wide county-level power outage data to estimate geographic clustering and association between outage exposure (distribution and duration) and six measures of racial, social, political, and/or medical vulnerability: Black and Hispanic populations, the Centers for Disease Control and Prevention (CDC) Social Vulnerability Index (SVI), Medicare electricity-dependent durable medical equipment (DME) usage, nursing homes, and hospitals. To examine individual-level experience and preparedness, we used a preexisting and non-representative internet survey. At the peak of the Texas Power Crisis, nearly 1/3 of customers statewide (N = 4,011,776 households/businesses) lost power. We identified multiple counties that faced a dual burden of racial/social/medical vulnerability and power outage exposure, after accounting for multiple comparisons. County-level spatial analyses indicated that counties where more Hispanic residents resided tended to endure more severe outages (OR = 1.16, 95% CI: 1.02, 1.40). We did not observe socioeconomic or medical disparities. With individual-level survey data among 1038 respondents, we found that Black respondents were more likely to report outages lasting 24+ hours and that younger individuals and those with lower educational attainment were less likely to be prepared for outages. Power outages can be deadly, and medically vulnerable, socioeconomically vulnerable, and marginalized groups may be disproportionately impacted or less prepared. Climate and energy policy must equitably address power outages, future grid improvements, and disaster preparedness and management.

Economic and mathematical model of enterprise client base management

Despite a fairly wide range of developed models for customer base management, the practice of implementing full-fledged customer base management models of the company is quite small. This is primarily due to the complexity and high cost of implementing a comprehensive model of managing the company’s customer base. The problem also lies in the limitations of the models themselves. Typically, the need to manage their company’s customer base arises in companies with a customer base of several thousand to millions of customers. In this case, the implementation of methods and approaches aimed at managing one client is not rational, and you need models adapted to work with groups of clients. An important limitation in existing research are the parameters of clustering the client base. Most authors suggest that the number of purchases and the age of the last purchase by the customer be considered as a criterion for division into groups of customers. This does not take into account such parameters of customer purchasing behavior as the amount of purchases, the value of the customer to the company and the time of interaction between the customer and the company.

A Comparative and Performance Analysis of Similarity Metrics in Recommender System Based on Hadoop Framework

With exponential growth of information available on web, there is a need for a personal assistance to customers for finding the best item out of the large set of items. There is also need for finding the best item having highest popularity. The personal assistance which will assist the user is the Recommender System. It is a software tool that uses knowledge discovery techniques to produce personalized recommendations. The majority of the recommendations are based on the machine learning algorithm and techniques which uses a standard data set for producing predictions. With tremendous growth of customers and items in the recent years, there is a key challenge for the recommendation system to produce quality recommendations based on the similarity of the users. There also lies a great challenge for the recommendation system to produce quality output when data set is huge, reduce latency, group users having similar interest and perform recommendations in seconds for millions of customers and products. Thus there is a need for new recommendation technologies which will produce quality output to users having similar tastes in a best possible manner. In this paper we present a comparative analysis of various similarity metrics used in recommendation system for clustering the users based on hadoop framework. The experimental results show that spearman rank correlation performs the best among the other similarity metrics based on three evaluation metrics.

Artificial Intelligence Driven Chatbot

Today, most large-scale conversational AI agents (e.g. Alexa, Siri, or Google Assistant) are built using manually annotated data to train the different components of the system. Typically, the accuracy of the ML models in these components are improved by manually transcribing and annotating data. As the scope of these systems increase to cover more scenarios and domains, manual annotation to improve the accuracy of these components becomes prohibitively costly and time- consuming. In this paper, a group of Amazon researchers propose a system that leverages user-system interaction feedback signals to automate learning without any manual annotation. Users here tend to modify a previous query in hopes of fixing an error in the previous turn to get the right results. These reformulations, which are often preceded by defective experiences caused by errors in ASR, NLU, ER or the application. In some cases, users may not properly formulate their requests (e.g. providing partial title of a song), but gleaning across a wider pool of users and sessions reveals the underlying recurrent patterns. The proposed self-learning system automatically detects the errors, generate reformulations and deploys fixes to the runtime system to correct different types of errors occurring in different components of the system. The results show that the approach is highly scalable, and able to learn reformulations that reduce Alexa-user errors by pooling anonymized data across millions of customers.

Optimizing JMeter on Performance Testing Using the Bulk Data Method

Company X is one of the companies engaged in the telecommunications business. To improve customer service, the company developed an Application Programming Interface). The developed API is used to promote product packages to customers. Sending data via API to millions of customers at the same time, can lead to failures due to the inability of the server to process that data. JMeter is one of the tools that can be used to perform performance testing of an API by providing TPS calculation output. Bulk data files are used as input to process large amounts of customer data on JMeter. Proper thread properties settings affect the TPS value, and the study has managed to achieve the TPS value to be achieved with error rate = 0, which means success.

Towards privacy compliance: A design science study in a small organization

Complying with privacy regulations has taken on new importance with the introduction of the EU’s General Data Protection Regulation (GDPR) and other privacy regulations. Privacy measures are becoming a paramount requirement demanding software organizations’ attention as recent privacy breaches such as the Capital One data breach affected millions of customers. Software organizations, however, struggle with achieving privacy compliance. In particular, there is a lack of research into the organizational practices and challenges involved in compliance, particularly for small and medium enterprises (SMEs), which represent a sizeable portion of organizations. Many SMEs use a continuous software engineering (CSE) approach, which introduces additional adoption and application challenges. For example, the fast pace of CSE makes it harder for SMEs that are already more resource constrained to prioritize non-functional requirements such as privacy.

A matheuristic for a customer assignment problem in direct marketing

In direct marketing, companies use sales campaigns to target their customers with personalized product offers. The effectiveness of direct marketing greatly depends on the assignment of customers to campaigns. In this paper, we consider a real-world planning problem of a major telecommunications company that assigns its customers to individual activities of its direct marketing campaigns. Various side constraints, such as budgets and sales targets, must be met. Conflict constraints ensure that individual customers are not assigned too frequently to similar activities. Related problems have been addressed in the literature; however, none of the existing approaches cover all the side constraints considered here. To close this gap, we develop a matheuristic that employs a new decomposition strategy to cope with the large number of conflict constraints in typical problem instances. In a computational experiment, we compare the performance of the proposed matheuristic to the performance of two mixed-binary linear programs on a test set that includes large-scale real-world instances. The matheuristic derives near-optimal solutions in short running times for small- to medium-sized instances and scales to instances of practical size comprising millions of customers and hundreds of activities. The deployment of the matheuristic at the company has considerably increased the overall effectiveness of its direct marketing campaigns.

DNN Patching: Progressive Fixing and Augmenting the Functionalities of DNNs for Autonomous Vehicles

Autonomous vehicles have become one of the most-awaited technologies of the century. In the recent years the advances in the area of deep learning and artificial intelligence enabled rapid development of the autonomous driving sector. Some car companies have already deployed autonomous driving software into their vehicles and millions of customers are using them. Although the autonomous driving modules are typically extensively tested prior to its release on the market, the customers can either still encounter certain previously overlooked failure cases or identify missing functionalities of the model. In this letter we focus on developing the methodology for repairing the deep neural network (DNN) steering the self-driving vehicle in response to these two scenarios via patching such that the following conditions are satisfied: i) the patch is added on the top of the original DNN to extend or fix its functionality for the particular failure case, ii) the patched model keeps the original functionalities of the DNN unchanged, and iii) the size of the patch is significantly smaller than the size of the original DNN. Our approach avoids training and evaluating the network from the scratch to improve or fix it, effectively enabling fast response of the autonomous vehicle manufacturers to the customer needs. We demonstrate the plausibility of the proposed approach on the task of autonomous driving in the Carla simulator A. Dosovitskiy <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">et al</i> .