Rao CasturiPart-Time Instructor Computer Science
B.E., Electronics and Communications, Andhra University
M.S., Computer Complexes, Systems and Networks, Tula State University
Ph.D., Computer Science, Georgia State University
FinTech, big data, databases, data mining, data analytics, software engineering, information technology, cloud computing, machine learning, behavior learning
I have extensive industry work experience (28+ years) in information technology, risk management (investment as well as operational risk), and teaching. I am currently working as V.P. Risk Reporting & Technology Solutions at Voya Investment Management (full-time) and as a part-time instructor at Georgia State University teaching various classes in computer science. I bring industry experience to the classroom and help my students solve real-world problems.
My areas of interest revolve around big data and FinTech-related software development methodologies, along with data mining techniques for constructing various financial applications. The purpose of my research is to design and develop a cost-effective and efficient enterprise framework in a cloud-computing environment for data mining and machine learning using a rule-based aggregation engine along with parallel processing of user-defined financial calculations to enable predictive analysis and knowledge discovery with a business intelligence reporting capability.
Turning raw data into meaningful information and converting it into actionable tasks makes organizations profitable and sustains immense competition. In the past decade we have seen an increase in the use of data-mining algorithms and tools in financial market analysis, consumer products, manufacturing, insurance, social networks, scientific discoveries, and warehousing. Building an efficient data-mining framework is expensive and usually requires a multiyear project for an organization. The elasticity of cloud architectures solves the hardware constraint for businesses. Effective aggregation using selective cuboids and parallel computations using Azure Cloud Services are two of many proposed techniques that fall into my research area. Our research produced a nimble, scalable, portable architecture for enterprise-wide implementation of DM (data mining) and ML (machine learning) frameworks.
“Enterprise Data Mining & Machine Learning Framework on Cloud Computing for Investment Platforms,” which I proposed and built during the research, is directly used in the investment risk management, portfolio, and asset management decision-making process, adding value to the organization. My research was focused on building the needed building blocks for an efficient, reusable, and flexible data schema structure for any enterprise data-mining applications. Using these techniques, organizations can save money by shortening the time required to develop software for their financial technology platform.
In the next phase of my research, I am focusing on “behavior machine learning,” which can be helpful for solving financial and socioeconomic problems that quantitative models currently cannot handle. With big data and historical analysis, mining the outliers and understanding the “snapshot behavior and outcome” can be very interesting.
R. Casturi and R. Sunderraman, A case study of enterprise machine learning framework for investment platforms, ICT for Competitive Strategies: Proceedings of the 4th International Conference on Information and Communication Technology for Competitive Strategies (ICTCS 2019), 2019, pp. 397–402.
R. Casturi and R. Sunderraman, Enterprise framework for business intelligence tools on cloud computing environment for investment platforms, Proceedings of the 9th International Conference on Information Systems and Technologies (ICIST 2019), 2019, pp. 1–7. https://doi.org/10.1145/3361570.3361574
R. Casturi and R. Sunderraman, Distributed financial calculation framework on cloud computing environment, Proceedings of the 6th International Conference on Big Data Analytics (BDA 2018), Lecture Notes in Computer Science, vol. 11297, Springer, 2018, pp. 73–88. https://doi.org/10.1007/978-3-030-04780-1_5
R. Casturi and R. Sunderraman, Cost effective, rule based, big data analytical aggregation engine for investment portfolios, Wireless Networks, 2018. https://doi.org/10.1007/s11276-018-01904-5
R. Casturi and R. Sunderraman, Script based migration toolkit for cloud computing architecture in building scalable investment platforms, Database and Expert Systems Applications: DEXA 2018 International Workshops, Communications in Computer and Information Science, vol. 903, Springer, 2018, pp. 46–64. https://doi.org/10.1007/978-3-319-99133-7_4
R. Casturi, Design and development of an efficient calculation framework for internal rate of return (IRR) of a fixed income portfolio with SIMD architecture, International Journal of Emerging Technology and Advanced Engineering, vol. 4, no. 9, 2014, pp. 17–22. http://www.ijetae.com/files/Volume4Issue9/IJETAE_0914_04.pdf