CLINTA PUTHUSSERY VARGHESE
  • Home
  • Projects

On this page

  • My Projects in R:
    • NOV 2024 | Data-Based Evaluation of Third-Party Assertion:
    • OCT 2024 | Data-Based Support for Sales Pitch:
    • SEPT 2024 | Descriptive Statistical Analysis:
  • IN Progress:
    • DEC 2024 | Data-Driven Decision Support:

Projects

My Projects in R:

NOV 2024 | Data-Based Evaluation of Third-Party Assertion:

Do Proportional Electoral College Allocations Yield a More Representative Presidency?

In this analysis, I investigated the impact of different state-level electoral vote allocation methods on presidential election outcomes. I compared various allocation strategies, assessed fairness and proportionality, and created visualizations like red/blue electoral maps using data from the MIT Election Lab and the US Census Bureau’s TIGER repository.

OCT 2024 | Data-Based Support for Sales Pitch:

Exploratory Data Analysis and Movie Analysis

This project positioned me as a Hollywood development executive, analyzing large-scale IMDb data to pitch a new movie. I developed proficiency in handling large datasets and relational data structures through techniques like table joins, enhancing my skills in managing and interpreting extensive information.

SEPT 2024 | Descriptive Statistical Analysis:

Fiscal Characteristics of Major US Public Transit Systems

I investigate the fiscal characteristics of US public transit authorities. In this project, I handle the data import and tidying; students are mainly responsible for “single table” dplyr operations (mutate, group_by, summarize, select, arrange, rename) to produce summary statistics.

IN Progress:

DEC 2024 | Data-Driven Decision Support:

Monte Carlo-Informed Selection of CUNY Retirement Plans

For this project, I conducted a comparative analysis of two CUNY retirement plans using Monte Carlo simulations. By incorporating historical financial and macroeconomic data, I assessed the probability of different retirement outcomes. This experience included working with APIs, implementing complex simulations, and applying bootstrap inference techniques to quantify prediction uncertainties.