Forecasting the 2019 Lok Sabha Election using Machine Learning and Data Analysis
This Python project seeks to forecast the election results of the General Election, 2019 in India using Data Analysis and Machine Learning.
The project report (PDF) can be found here.
Description
The General Election in India which will be contested for 545 seats in the Lok Sabha.
Major focus would be given to a potential extended alliances that may be the deciding factor in the contest.
Data Analysis would be used to parametrize computations such as coalitions and swings on all the seats. After that, Machine Learning algorithms such as Linear Regression can be utilized to calculate the aforementioned swing parameters using past election data specific to the relevant seats.
A large corpus of recent articles and/or twitter tweets can be used to calculate moods relevant to the elections. With the appropriate biases based on subjective data, we may be able to apply swings to the vote shares of each party in each constituency, and obtain viable forecasts.
Tools/frameworks/libraries used:
- Jupyter Notebook
- WEKA Machine Learning Suite (for finding election swings using Machine Learning)
- Pandas library (for reading large data customizing coalitions using Data Analysis)