The problem Job Scouter solves

It matches the applicants resume with companies needs. Its basically matches the keyword that we are extracting from the resume and matching it with the companies job profile. It also shows the accuracy of the applicant using the ML model.

Challenges we ran into

While creating our full stack AI/ML application, we faced several challenges:

1. Collecting data: Gathering relevant and high-quality data was time-consuming and required careful selection of reliable sources.

2. Removing stop words: We encountered issues when removing common words from resumes, as it was essential to maintain accuracy without losing valuable information.

3. Accessing LinkedIn API data: Retrieving data from LinkedIn's API posed its own set of difficulties, including authentication and secure data retrieval.

4. Reading and parsing API data: We had to process and present the API data in a user-friendly format, ensuring correct interpretation and seamless user experience.

5. Integrating Python scripts with Node.js: Running a Python script within the Node.js runtime required bridging the gap between the two languages effectively.

6. Accessing sufficient data for model training: Obtaining enough diverse and high-quality data for training our models proved to be a challenge.

Despite these obstacles, we conducted research, sought guidance, and applied problem-solving skills to create a robust and user-friendly AI/ML application.