Learning Management System SSSIHL

SSSIHL ACTUARIAL RESEARCH PROGRAM

SSSIHL Masters Program in Actuarial Science

SSSIHL Actuarial Science Program was designed by several leading Actuaries in the industry with the motive to bridge the gap present between the Academia and the Industry. The students in the span of 2 years are not only trained to clear Actuarial Science papers but also in various important skill sets and experience the industry expects of in a student. The program recognizes the increasing need for programming and data science in the insurance industry. Thus, training its students in advanced programming and data science techniques and its applications in the insurance industry. Thus, the students are enabled to solve various actuarial problems by the integration of Actuarial Science and Data Science.

The program is developed for M.Sc. Mathematics students as a specialization. A student going through this course must go through 8 Actuarial Science Papers, 4 Lab courses, 10 Papers in Pure and Applied Mathematics, and 1 Live Project. The Actuarial Science Syllabus at SSSIHL is oriented towards the syllabus of the Institute and Faculty of Actuaries (IFoA – UK), Casualty Actuarial Society (CAS – USA), and Institute of Actuaries (IAI – India).

SSSIHL PhD. Program in Actuarial Science

Apart from the Masters' program, SSSIHL also provides its students with a platform to pursue Actuarial Science Research. The program aims at addressing Macro Level problems in the insurance industry. The Research at SSSIHL is interdisciplinary wherein the PhD students collaborate with the final year M.Tech Computer Science students. There are 2 Students at the moment Pursuing Actuarial Science Research in our institute

• Rohan Yashraj Gupta – Working to come up with a Comprehensive Data-Driven Fraud Detection and Prevention solutions for Insurance Industry
• S.R.Pranav Sai – Working to come up with an ERM Dashboard with predictive analytics to enhance the Operational Efficiency of the Insurance Industry.

Both the students in the last 1 year of their research have published about 6 Research Papers and book chapters combined with 4 conference proceedings combined.

Papers Published

Published about 20 Tech Actuarial - Research Papers in International Journals with titles:

• Book chapter titled - Application of Cart-Based Modeling in Motor Insurance Fraud - Intelligent System Algorithms and Applications in Science and Technology, CRC Press Taylor & Francis, 2021
• Book chapter titled - Application of Neural Networks for Assessing the Performance of Insurance Business - Intelligent System Algorithms and Applications in Science and Technology, CRC Press Taylor & Francis, 2021
• TGANs with machine learning models in automobile insurance fraud detection and comparative study with other data imbalance techniques, International Journal of Recent Technology and Engineering, 2021
• Implementation of Correlation and Regression Models for Health Insurance Fraud in Covid-19 Environment using Actuarial and Data Science Techniques, International Journal of Recent Technology and Engineering, Sep. 2020
• Assessing the sustainability of General Insurance Business through Real Time Monitoring of KPIs using Recurrent Neural Network - International Journal of Recent Technology and Engineering, 2020.
• An analytical model for evaluating social security schemes-A focus on ‘Ayushman Bharat’ universal health scheme in India, International Journal of Recent Technology and Engineering, 2019.
• Implementation of a Predictive Model for Fraud Detection in Motor Insurance using Gradient Boosting Method and Validation with Actuarial Models, in 2019 IEEE International Conference on Clean Energy and Energy Efficient Electronics Circuit for Sustainable Development (INCCES), 2019
• Assessing Sustainability of General Insurance Business through Real Time KPI using GPUs and Neural Networks, - International Journal of Recent Technology and Engineering, Dec. 2019. 
• Application of High-Performance Computing for Calculating Reserves using the Cape Cod Method, International Journal of Engineering and Advanced Technology, Oct. 2019.
• A Proposed Model for Measuring Protection of Policyholders ’ Interest at Industry Level, Journal of Insurance Regulatory Development Authority of India, 2019
• Deep Representation Learning using Stacked Autoencoder for Claim Reserve Prediction, 2019
• Blockchain Technology in Health Insurance – Integration of 8 Stakeholders, International Journal of Scientific & Engineering Research, 2019.
• SSSIHL Data Cleaning Framework, International Journal of Scientific & Engineering Research, 2019.
• A Framework for Comprehensive Fraud Management using Actuarial Techniques, International Journal Scientific and Engineering Research, 2019.
• Measuring the Effectiveness of VaR in Indian Stock Market, International Journal of Engineering Trends and Technology, 2018.
• Use of Blockchain Technology in integrating Heath Insurance Company and Hospital, International Journal of Scientific and Engineering Research, 2018.
• Fraud Detection Supervised Machine Learning Models for an Automobile Insurance, International Journal of Scientific and Engineering Research, 2018.
• Risk-Based Approach to Calculate General Motor Insurance Reserve using High-Performance Computing, International Journal of Engineering Trends and Technology, Nov 2018.
• Application of High-Performance Computing for Calculation of Reserves for a Company, International Journal of Scientific & Engineering Research, 2018.

Conferences

• R. Y. Gupta and G. U. Sankar, “A proposed unsupervised learning approach for fraud detection in automobile insurance using Apache Spark,” in International Virtual Conference on Distributed Computing, Intelligence & it’s Applications IVCDCIA, 2020, 2020.
• R. Y. Gupta, S. Sai Mudigonda, P. K. Kandala, and P. K. Baruah, “Implementation of a Predictive Model for Fraud Detection in Motor Insurance using Gradient Boosting Method and Validation with Actuarial Models,” in 2019 IEEE International Conference on Clean Energy and Energy Efficient Electronics Circuit for Sustainable Development (INCCES)
• S. R. Pranav Sai, A. S. Pawar, S. S. Mudigonda, and P. K. Baruah, “Application of High-Performance Computing for Calculating Reserves using the Cape Cod Method,” presented at 2019 HiPC conference
• S. R. P. Sai, P. K. Kandala, S. S. Mudigonda, and P. K. Baruah, “Assessing Sustainability of General Insurance Business through Real Time KPI using GPUs and Neural Networks,” in 2019 IEEE International Conference on Clean Energy and Energy Efficient Electronics Circuit for Sustainable Development (INCCES)
• Deep Representation Learning using Stacked Autoencoder for General Insurance Loss Reserving, presented at Insurance Data Science Conference, Zurich, Switzerland Jun 2019
• Approach to evaluate the impact of auto regulations 2017 – Insights from invisibles, Global Conference of Actuaries, Mar 2019

Capabilities in Actuarial Data Science

• Data Cleaning: We offer an automated approach for Data Cleaning. Our methodology involves the usage of distributed systems for big data.
• Dashboard: We have a framework to create an Enterprise Risk Management dashboard for businesses. Our approach is forward-looking and involves Artificial Intelligence techniques in combination with Actuarial technique.
• Business As Usual Reporting: We offer Business As Usual (BAU) reports with portfolio level Data Analytics and Data Visualizations with Descriptive analysis, Predictive analysis,  Prescriptive analysis  
• Financial Condition Reporting: We help with the compilation and preparation of Financial Condition Report of your company using Machine learning techniques.
• Rate Making and IBNR Reserving: We offer a wide range of Actuarial, statistical and machine learning capability that can adapt depending on the risk being modelled and the level of data available. Data Science applications for automated Feature Engineering, risk factor identification, stochastic claims prediction are some examples. 
• Product Pricing: We have experience in building pricing models in various software like EMBLEM, Python, R and SAS. We follow a mix of Actuarial and data science methods to design and price insurance and reinsurance products spanning across the product value chain.
• Reserving: We follow a mix of Actuarial and data science methods to model, triangulate claims data to compute IBNR and reserve requirements. 
• Pensions and Employee Benefits: Actuarial Valuation of defined benefits, defined contribution, gratuity, leave encashment and ESOPs. We also provide advisory services on pension fund investment strategies
• Fraud Detection: We have done extensive research in fraud detection modelling. Our Comprehensive Fraud Detection Framework adapts to the level of data available CART based Models, Deep learning,  Trigger-based systems.
• Sales Campaigns: An effective predictive modelling approach helps companies decide on the right market segment to target for Sales campaigns. Our models help with target market identification and Hit Ratio maximization for campaigns.
• Clustering: We have strong research-backed clustering techniques that help with risk classification, fraud detection etc.
• Customer Lifetime Value: Customer lifetime value is an important aspect for new business acquisition, renewals and portfolio strategy of the company. We follow a hierarchical approach towards modelling customer lifetime value that involves statistical and machine learning methods with Actuarial interpretation.
• Process Automation: We help upgrade spreadsheet-based processes into more advanced software like Python, R and SAS.