Search results

Predictive analytics is the science of decision-making that eliminates guesswork out of the decision-making process and applies proven scientific procedures to find right solutions. Predictive analytics provides ideas on the occurrences of future downtimes and rejections thereby aids in taking preventive actions before abnormalities occur. Considering these advantages, predictive analytics is adopted in various diverse fields such as health care, finance, education, marketing, automotive, etc. Predictive analytics tools can be used to predict various behaviors and patterns, thereby saving the time and money of its users. Many open-source predictive analysis tools namely R, scikit-learn, Konstanz Information Miner (KNIME), Orange, RapidMiner, Waikato Environment for Knowledge Analysis (WEKA), etc. are freely available for the users. This chapter aims to reveal the best accurate tools and techniques for the classification task that aid in decision-making. Our experimental results show that no specific tool provides the best results in all scenarios; rather it depends upon the datasets and the classifier.

The healthcare sector in India is witnessing phenomenal growth, such that by the year 2022, it will be a market worth trillions of INR. Increase in income levels, awareness regarding personal health, the occurrence of lifestyle diseases, better insurance policies, low-cost healthcare services, and the emergence of newer technologies like telemedicine are driving this sector to new heights. Abundant quantities of healthcare data are being accumulated each day, which is difficult to analyze using traditional statistical and analytical tools, calling for the application of Big Data Analytics in the healthcare sector. Through provision of evidence-based decision-making and actions across healthcare networks, Big Data Analytics equips the sector with the ability to analyze a wide variety of data. Big Data Analytics includes both predictive and descriptive analytics. At present, about half of the healthcare organizations have adopted an analytical approach to decision-making, while a quarter of these firms are experienced in its application. This implies the lack of understanding prevalent in healthcare sector toward the value and the managerial, economic, and strategic impact of Big Data Analytics. In this context, this chapter on “Predictive Analytics in Healthcare” discusses sources, areas of application, possible future areas, advantages and limitations of the application of predictive Big Data Analytics in healthcare.

Background: Human resource management (HRM) is the tactical method for a business enterprise’s optimistic and systemic administration. This study aims to identify the common and major triggering attributes and the knowledge gap between HRM and an organisation’s employee attrition rate.

Method: The employee Attrition Case Study Dataset used is an anecdotal data set that tries to figure out relevant variables that determine employee behavioural aspects towards attrition. This study investigates why attrition occurs, the major triggering attributes for employee turnover, and how it might be anticipated to employ artificial intelligence (AI) to avert corporate losses.

Results: Employees’ monthly income, age, average monthly hours, distance from home, total working years, years at the company, per cent of salary hike, number of companies worked, stock options level, job role and other factors are taken into consideration. A feature importance extraction framework was devised to investigate the various dormant factors. The findings also show feasible hypotheses that help enhance employee engagement, reinvent the worker dynamic, and higher levels of risk decrease attrition rate.

Implications: Employees’ monthly income, age, average monthly hours, distance from home, etc., are all major variables in employee attrition in the Indian IT business. This research adds to the theory development of behavioural elements in people analytics based on AI.

Purpose: Can we predict employee attrition through employee behavioural patterns advancement using AI tools.

Prior research (Harrast, Olsen, & Sun, 2023) analyzes the eight emerging topics to be included in future CPA exams and discusses their importance to career success and appropriate teaching locus in light of survey evidence. They find that the general topic of data analytics is the most important of the eight emerging topics. To further understand the topics most important to career success, this study analyzes subtopics underlying the eight emerging topics. The results show that advanced Excel analysis tools, data visualization, and data extraction, transformation, and loading (ETL) are the most important data analytics subskills for career success according to professionals and that these topics should be both introduced and emphasized in the accounting curriculum. The results provide useful information to educators to prioritize general emerging topics and specific subtopics in the accounting curriculum by taking into account the most pressing needs of the profession.

Introduction: All countries are interested in attracting foreign direct investment (FDI) as it provides for productivity gains and modernisation for attaining sustainable development goals. Multinational corporations (MNCs) collect a vast volume of structured and unstructured big data when seeking international expansion by the FDI route in the insurance sector, but concluding these data may not be practically feasible. So nowadays, for finalising their FDI ventures, MNCs depend on machine-based algorithms for quick analysis of big data sets.

Purpose: This chapter explores how emerging big data analytics and predictive modelling fields can scale and speed up FDI decisions in the insurance sector.

Methodology: The author used a descriptive study based on secondary data from sources like World Bank, The Organisation for Economic Co-operation and Development (OECD), World Trade Organisation (WTO), and International Finance Corporation (IFC) data repositories to identify variables such as risks, costs, trade agreements, regulatory policies, and gross domestic product (GDP) that affect FDI movements. This chapter highlights the process flow that can be beneficial to convert big data sets using statistical tools and computer software such as Statistical Analytics Software (SAS), IBM SPSS Statistics.

Findings: The application of artificial intelligence-based statistical tools on FDI variables can help derive time-series graphs and forecast revenues. The authors found that foreign investors can narrow their prospect search for industry or product to manageable from varied investment opportunities in host countries. Advancements in big data analysis offer cost-effective methods to improve decision-making and resource management for enterprises.

In today’s marketplace, accountants must understand and master Big Data and data analytics, and many educators have devised approaches to help students acquire these critical skills. At our university, we have worked closely with our accounting advisory council to develop an adaptable classroom case where students not only gain a broad understanding of what data analytics means to the profession but also what specific tools are available to analyze an accounting-centered problem – cash collections. Using patterns and behaviors discovered in their data analyses, students develop collection procedures and controls for a case firm. Such a project begins to fulfill the profession’s initiative that accountants must exploit Big Data and data analytics for organizational growth and opportunity.

In recent years professional accountancy bodies (e.g., CPA), accreditation institutions (e.g., AACSB) and employers have steadily raised, and continue to raise expectations regarding the need for accounting graduates to demonstrate skills in data analytics. One of the obstacles accounting instructors face in seeking to implement data analytics, however, is that they need access to ample teaching materials. Unfortunately, there are few such resources available for advanced programming languages such as R. While skills in commonly used applications such as Excel are no doubt needed, employers often take these for granted and incremental value is only added if graduates can demonstrate knowledge in using more advanced data analytics tools for decision-making such as coding in programming languages. This, together with the current dearth of resources available to accounting instructors to teach advanced programming languages is what drives motivation for this chapter. Specifically, we develop an intuitive, two-dimensional framework for incorporating R (a widely used open-source analytics tool with a powerful embedded programming language) into the accounting curriculum. Our model uses complexity as an integrating theme. We incorporate complexity into this framework at the dataset level (simple and complex datasets) and at the analytics task level (simple and complex tasks). We demonstrate two-dimensional framework by drawing on authentic simple and complex datasets as well as simple and complex tasks that could readily be incorporated into the accounting curriculum and ultimately add value to businesses. R script programming code are provided for all our illustrations.