Authors:

Thanmaya Pattanashetty

Date Created:

Not specified

Course Title:

Professor:

Not specified

About Paper:

With the upcoming elections, a common goal is to predict the outcome of the election. The process of forecasting involves uncertainty and close inspection from the public. Other organizations have created their own forecasting approaches, however many organizations are not fully transparent about their methods. Our research intends to forecast the outcome of the 2024 presidential, senatorial, and gubernatorial elections while keeping all methods and code publicly available and accessible. The mathematical model that we use is an adapted Susceptible-Infected-Susceptible (SIS) model, and this basic framework, which is quite flexible, was originally used to describe interactions between susceptible and infected individuals during disease transmission. We implement an altered version of this model where we simulate the dynamics of Democratic, Republican, and undecided voters in each state. To determine our model parameters, we use polling data gathered from the organization FiveThirtyEight. Another goal of our research is to improve the accuracy of our methods by accounting for partisan lean within the pollster organizations that produce polling data. When gathering data, pollsters' methodologies may result in partisan lean which could skew forecasts. By incorporating this potential partisan lean into our election model, the results may be more accurate. As an additional method, we also plan to investigate giving more weight larger to polls with larger sample sizes. Lastly, displaying forecast results to the public includes creating engaging visualizations that display useful knowledge about the election. Our forecasts and visualizations for this upcoming year's election will be posted on https://c-r-u-d.gitlab.io/2024/ throughout this election season. Keywords: Differential Models; Mathematical Models; Political Science; Forecast Models

Source:

Purdue University / 2024

Topics:

No topics listed

Co-authors:

Thanmaya Pattanashetty