Dr. Suresh has done high quality research work in the area of Statistics and Reliability Modeling with a post-PhD experience (a mix of industry and academics) of over 30 years. He served as the Principal Director in Supply Chain Analytics in Accenture Applied Intelligence. In the past, he has worked at General Motors Research & Development centre India Science Lab (ISL) at Bangalore as Staff Researcher.

Dr. Suresh had worked as Professor at Indian Institute of Management Kozhikode (IIMK) for over a decade and also at Departments of Statistics at University of Pune and MS University of Baroda as Faculty. Suresh had taught at Victoria Management School of Victoria University of Wellington, New Zealand as a Visiting Professor in 2006.

A high quality researcher, Dr. Suresh has published more than 30 papers in reputed national/ international journals in Statistics. Most of his work has been cited in various other research works, amounting to a total of over 400 citations.

He has been a reviewer for many leading journals in Statistics. An estimation method from his work is commonly referred to as Tiku-Suresh Method in the literature. Suresh has contributed substantially in the estimation of Reliability and change-point in a failure rate function. These results are of immense use in industry in arriving at decisions relating to warranty period.

Suresh has delivered invited lectures at leading institutions such as Indian Institute of Science, Indian Statistical Institute, Department of Mathematics and Statistics of Victoria University, New Zealand, Statistics New Zealand besides many universities in India. Suresh has provided training and consultancy to various organizations including Department of Telecommunications, Government of India, Hindustan Newsprints Ltd., WIPRO Ltd., Kirloskar Cummins, Tata Tea Ltd, IPS and IES Officers Training Institutes etc.

Suresh has established himself as an innovative thought leader in the Analytics industry over the past decade, and many of his ideas and methodologies have been implemented in the industry yielding greater savings/ benefits.

In 2009, Suresh received a GM R&D Innovation Award (McCuen Special Achievement Award) for extraordinary contributions to the identification of Price of Entry and Key Wins, and also received GM India President's honour in2010. Suresh received the Best Young Statistician Award from Indian Society for Probability and Statistics in 1991, and also received two Gold Medals from Mysore University in 1986.

• PhD (University of Pune ) - Statistics 1991
• MSc (University of Mysore) - Statistics 1985
• BSc (University of Madras) - Statistics 1983

• Exploring Data Science
• Statistics with R; Introduction to Statistics and Data Analysis
• Operations Management; Quality Management; Quantitative Techniques for Marketing Research; Six Sigma
• Research Methodology – for PhD

• Statistical Inference
• Reliability and Survival Analysis
• Healthcare Analytics

• A new method of estimation of location and scale parameters
  Journal of Statistical Planning and Inference. 1992, 30, 281-292. (with M.L.Tiku)
  Number of Citations: 175 – Over 30 citations since 2020
• Multi-step sales forecasting in the automotive industry based on structural relationship identification
  International Journal of Production Economics, 2012, 140(2), 875-887. (Jointly with Sa-ngasoongsong A, Bukkapatnam S T S, Kim J and Iyer, P)
  Number of Citations: 93; Over 50+ citations since 2020
• Non-monotonic ageing
  Scandinavian Journal of Statistics, 1990, 17, 257-262. (with J.V.Deshpande)
  Citations: 36; 12+citations since 2020
• Acceptance sampling plans by variables for a class of symmetric distributions
  Communications in Statistics – Simulations and Computation, 1997, 26(4), 1379-1391. (with T.V.Ramanathan.)
  Citations: 35; 5+ citations since 2020
• Improving Blast Furnace Operations through Advanced Analytics
  Chapter 10, Advances in Analytics (Ed.) Arnab Laha (2021) (Jointly with Rishabh Agrawal)
• Implementation of Six Sigma in the service industry
  Effective Executive, 2005, Vol. VII, No.1, 12-18. (Jointly with Gurvinder Singh)

Predicting Failures with Incomplete Data

In Automotive industry and in most other industries, it is of interest to predict failures of products and components thereof, so as to help engineers, financial managers and supply chain managers in taking appropriate Warranty decisions (e.g., extension of warranty), in determining warranty reserve fund, in determining stock levels of spare parts, in providing alerts to customers, and also in arriving at bulk replacement or recall decisions. For most components, the manufacturers have the failures data only until the warranty period, and the data that exist beyond warranty period are not very reliable or largely incomplete. Hence the prediction of failures beyond warranty period needs to be based primarily on failure data during warranty period. Some parametric based models exist in the literature, and by estimating the parameters based on the data till the warranty period. However, since typically, 3-4% of items / parts fail in the warranty period, such parameter estimates may not be reliable.
In this project, we develop some approaches to estimate the failures beyond the warranty period using the behavior / properties of the normalized spacings of order statistics observed till the warranty period. We validate the method with specific data sets.

Study of Reliability of AI systems

Artificial Intelligence is now seen in every activity, and has been playing a major role in everyday life. These systems have allowed one to go beyond limited human cognitive ability into understanding the complexity in the high dimensional data. For example, medical sciences have seen a steady use of these methods but have been slow in adoption to improve patient care (see, e.g., Balagurunathan, Mitchell and Naga (2021) “Requirements and Reliability of AI in medical context” Physica Media, Vol 83, p 72-78). There are some significant impediments that have diluted this effort, which include availability of curated diverse data sets for model building, reliable human-level interpretation of these models, and reliable reproducibility of these methods for routine clinical use. Similar is the case in other application areas as well, such as Finance, Operations etc. Maintaining high reliability of the components of the AI systems, and of the AI system itself, are needed, so as to increase the usability and to increase the confidence among the users/ customers of the products/ services delivered by AI systems. This project aims to identify various components of Reliability of AI systems and develop methods to ensure highly reliable AI systems.

Intelligent Supply Chain models with social media and other external inputs

Supply chains encompass the companies and the business activities needed to design, make, deliver, and use a product or service. Businesses depend on their supply chains to provide them with what they need to survive and thrive. Every business fits into one or more supply chains and has a role to play in each of them. In modern global market, one of the most important issues of the supply chain (SC) management is to satisfy changing customer demands and enterprises should enhance the long-term advantage through the optimal inventory controlaas well as with
optimal networks and logistics. In this project, we plan to develop a framework for developing Intelligent Supply Chain systems by sensing changing customer needs using inputs from external sources such as Social media, global climate changes, demographic changes etc.

Co-supervisor to: Amit Sharma