Skip to content

Classification Model to predict the Election Poll results for winning party

Notifications You must be signed in to change notification settings

Karthi18raj/Election-Exit-Poll-Prediction

Repository files navigation

Based on the predictions from the RF model, the insights for the Election are • The vote of a respondent is based on the importance of his attitude towards these features with top 5 being the most important. ✓ Hague ✓ Europe ✓ Blair ✓ age ✓ political.knowledge ✓ economic.cond.national ✓ economic.cond.household ✓ gender • The Attitude of the people towards, Hague, Blair and EU influence the voters most. • Hague needs to increase his popularity among the voters to win the election. • Blair already has huge popularity. • Blair has huge support among the voters and he has twice the vote as Hague. • Hague supporters are split into two categories 1. Supporters who have good opinion and vote for him 2. Supporters who have good opinion and didn’t vote for him. • The second case has to be analysed further by the party to find the reason for those behaviours. • Based on the predictions, Blair has the upper hand in the election. It is predicted that the Labour party might win with huge margins. • Based on the Business Problem, whether to predict which party votes accurately, the model can be used for that problem statement with the respective Precision/Recall Measures. • As a Final Model, RF and LDAB will the best ones to make predictions. With AUC also into consideration, LDAB can be used for better predictions.

About

Classification Model to predict the Election Poll results for winning party

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published