• Basics of analytics and big data

      Dinesh Kumar, U.; Pradhan. M.; Ramanathan, Ramakrishnan (CRC Press, Taylor & Francis, 2017-07-17)
      In this book chapter, we introduce fundamental concepts of analytics and big data and role of analytic in multi-criteria decision making.  Three components of analytics, namely, descriptive, predictive and prescriptive analytics are explained using different applications of these three components.  The chapter also introduces big data challenges and technology used for handling big data problems.  The primary objective of the chapter is to introduce basic concepts in analytics and big data to the readers.
    • Big data analytics using multiple criteria decision making models

      Ramanathan, Ramakrishnan; Mathirajan, Muthu; Ravindran, A. Ravi (CRC Press, Taylor & Francis, 2017-07-17)
      The field of multi-criteria decision-making (MCDM) assumes special importance in this era of Big Data and Business Analytics (BA). Big Data and BA are relatively recent phenomena, and studies on understanding the power of Big Data and BA are rare with a few studies being reported in the literature. While there are several textbooks and research materials in the field of multi-criteria decision-making (MCDM), there is no book that discusses MCDM in the context of emerging Big Data. Thus, the present volume addresses the knowledge gap on the paucity of MCDM models in the context of Big Data and BA. The book has 13 chapters. The first chapter is Festschrift in Honor of Professor Ravindran (which has been the primary purpose for developing this book) by Professor Adedeji B Badiru. The rest of the volume is broadly divided into three sections. The first section, consisting of chapters 2 and 3, is intended to provide the basics of MCDM and Big Data Analytics. The next section, comprising of Chapters 4-10, discusses applications of traditional MCDM methods. The last section, comprising of the final three chapters, discusses the application of more sophisticated MCDM methods, namely, Data Envelopment Analysis and the Analytics Hierarchy Process. The chapters are aimed to illustrate how MCDM methods can be fruitfully employed in exploiting Big Data, and it is hoped that this book will kindle further research avenues in this exciting new field.  This book will serve as a reference for MCDM methods, Big Data, and linked applications.
    • Multi-criteria decision making: an overview and a comparative discussion

      Ramanathan, Ramakrishnan; Mathirajan, Muthu (CRC Press, Taylor & Francis, 2017-07-17)
      An attempt to provide an overview of the different techniques in the field of multi-criteria decision-making is made in this chapter. First, some basic terminologies are reviewed. A classification of the various methods is outlined. Some of the basic concepts common to many methods are presented. The methods covered in the overview include the Multi Attribute Utility Theory, the Analytic Hierarchy Process, the ELECTRE methods, PROMETHEE methods, Fuzzy Set Theory, Multi-objective Linear Programming, Goal Programming, the Aspiration-level Interactive Method, Compromise Programming, and Data Envelopment Analysis. The different methods are compared in terms of several vital parameters. Finally, a link to the context of Big Data is provided in line with the theme of this book.
    • The use of DEA for studying the link between environmental and manufacturing performance

      Ramanathan, Ramakrishnan (CRC Press, Taylor & Francis, 2017-07-17)
      In this era of big data and business analytics, huge data is available in public domain and it is important for researchers to analyse this data to be able to make business sense to help businesses grow and to help policy makers to obtain useful insights. In this chapter, we first outline various available Big Data in the public domain that can be used to investigate an important issue in environmental policy: the relationship between environmental expenditure and manufacturing efficiency. We then illustrate how a multi-criteria tool, namely the Data Envelopment Analysis, can be advantageously combined with other statistical models to help study the above relationship. DEA is used to obtain manufacturing efficiency scores of various sectors in the UK. DEA scores are then combined with further data on pollution abatement expenditure in these sectors. Using previous literature, we hypothesise that there is a positive relationship between environmental expenditure and manufacturing efficiency of sectors, and verify it using sector-level data from the UK manufacturing industry. Our study illustrates the use of MCDM tools in using publicly available Big Data for use in public policy analysis.