Find_your_career_path

home page
display options
Selecting options
Result

Inspiration - students don't have proper guidance and take the career which they are not interested they choose that career with lack of knowledge but our web app fills this gap and it helps the student to find his career path in which he is good at in which he/she is interested in .

What it does - Choosing the right career is significant due to the diversified human abilities. Many

students are choosing their career path without receiving proper advice from suitable professionals or university services. This may potentially cause a mismatch between the academic achievements, personality, interests, and abilities of the students. In order to recommend students in career selection, it is essential to build a system that provides direction and guidance to students in choosing their career. The key challenge in this project is selecting key attributes that help in predicting the right path to meet diversified students’ goals. This Web application will be very useful for the students as an advisor in choosing their career course. The proposed framework for Find your Career Path is aimed at bridging the gap between students and career counselors. Here, we have developed a software tool to provide all the available degrees of different groups. This tool will help you determine and will eventually help you in choosing your own career path.

How we built it - To build a prediction application we initially need a dataset. We collected the data from various websites and prepared a dataset in CSV format. The dataset consists of schools,

Inter/Polytechnic/CBSE Board/ITI/Paramedical, groups, degrees, branches, and the output. Exploratory Data Analysis is done on the dataset i.e. pre-processing the data. The data is in the object datatype, the machine learning models predict the integral values. Used LabelEncoder to convert output column into int datatype and Used OneHotEncoder to convert input object datatype into int datatype. The data is split into training and testing data using the train_test_split function. We used linear regression model, k nearest neighbor, Support vector machine, and Decision trees for the prediction. We chose the linear regression model for the prediction since it has an accuracy score of 0.74. After using all the records, we are able to build a machine learning model (linear regression – best one) to accurately predict career prospects, Average Salary, and Higher education courses. A web application is built for this machine learning model using a flask. we will dump this machine-learning model into a pickle. In Python, pickling refers to storing a variable into a .pkl file.HTML ad CSS are used for the front-end. HTML is for building web pages, and CSS is for styling web pages. The .pkl file is called in the HTML file for prediction. Used JavaScript for the Backend to create a dynamic and interactive web.