Personality Prediction and Resume Screening using Machine Learning

DOI

No DOI

Published In

Volume 4, Issue 3 (2023)

Published Online

May-June 2023

Pages

421-423

Article Type

Research Article

Check for updates

No DOI available for cross-reference

Abstract: The personality of a human plays a major role in his personal and professional life. Many organizations have also started shortlisting the candidates based on their personality as this increase efficiency of work because the person is working in what he is good at than what he is forced to do The project is based on identifying the personality of an individual using machine learning algorithms and Model classify the personality The prediction of the personality of an individual is a critical problem in both areas whether it is considered in the context of organizations or in the case of our daily lives. Prediction of personality depends on many factors and these factors may vary from one individual to another. Personality prediction is identifying the personalities of individuals through their actions in different situations and observing their behaviour in various circumstances Five characteristics of different individuals commonly known as big five characteristics namely, openness, neuroticism, conscientiousness, agreeableness and extraversion are stored in a dataset along with gender and age of individual and used for training. Before training the model, data is preprocessed like handling missing values, data discretization, standardization etc. This pre-processed data is then used to train the model. User rates himself for different behavioural characteristics and based upon the information provided by the user his/her personality is predicted using trained ML model. Personality traits show the different characteristics of different people based on their thoughts The accuracy of personality prediction achieved by using Logistic regression Classifier is 75.25%. We refer to them as personality types. In this Project people with similar personalities are grouped together based on identifying personality models.