Voting is the right of every eligible citizen. It is the power vested upon the people which allows them to choose a party or a person who will represent them as a part of the government. On one side of the coin, are the people whereas on the other side, are the parties. Every election, a stupendous sum of money is spent by the parties in doing social work, promotion of candidates and many more such fields. Thus, it would be of strategic importance to a party, if they are able to predict the voting outcomes in an area in advance, as it can help them to carry forward their campaign judiciously. In this proposed work, a dataset from Show of Hands is used which contains multiple features, several of them hidden, which were discovered after data analytics. The aim is to correctly predict the party a person is most likely to vote for, in the USA presidential election. For this purpose, first after collecting the data, we perform data cleaning and feature extraction. Next, the data is given as input to our model. The model is trained using multiple machine learning algorithms like Logistic Regression, Support Vector Machine (SVM), Naïve Bayes Classifier and Random Forest. The accuracy of these models is compared and the prediction report is generated.

Voting, Data Analytics, Data Cleaning, Machine Learning

[1] Zolghadr, M. Niaki, S.A. Niaki, “Modelling and Forecasting US Presidential Election using learning algorithms”, International Journal of Industrial Engineering, Vol.14, Issue.3, pp.491-500, 2018.
[2] A. Wakjira, “Predicting voting Affiliation Using Machine Learning Algorithms ”, Metropolia Ammattikorkeakoulu Publisher,2014
[3] P. Kassraie, A. Modirshanechi and H. Aghajan, “Election Vote Share Prediction using a Sentiment-based Fusion of Twitter Data with Google Trends and Online Polls.”, In the proceedings of the 6th International Conference on Data Science, Technology and Applications (DATA 2017),pp.363-370.
[4] P. Salunkhe, S. Deshmukh, “Twitter Based Election Prediction and Analysis ”, International Research Journal of Engineering and Technology (IRJET), Vol.04, Issue.10, pp.539-544, 2017.
[5] Marie Fernandes , "Data Mining: A Comparative Study of its Various Techniques and its Process", International Journal of Scientific Research in Computer Science and Engineering, Vol.5, Issue.1, pp.19-23, 2017.
[6] A. Jenita Jebamalar, "Efficiency of Data Mining Algorithms Used In Agnostic Data Analytics Insight Tools", International Journal of Scientific Research in Network Security and Communication, Vol.6, Issue.6, pp.14-18, 2018.
[7] K. Sree Divya, P. Bhargavi, S. Jyothi, "Machine Learning Algorithms in Big data Analytics", International Journal of Computer Sciences and Engineering, Vol.6, Issue.1, pp.63-70, 2018.
[8] WEKA Manual for Version 3-6-8, The University of Waikato, 2012.