Resume Reviewer

Inspiration

The inspiration behind this project came from the frustration of seeing so many online ATS resume scanners locked behind paywalls. I wanted to challenge myself to create one from scratch and learn NLP along the way.

What it does

The website is straightforward, with three simple steps: upload your resume, select the job type, and provide a job description. This information is processed using an NLP library called SpaCy, which analyzes the text and compares your resume to the job type and description. Finally, a score is generated to show how well your resume aligns with the job you're targeting.

How we built it

I built the project using the SpaCy en_core_web_sm pipeline to interpret English. After the NLP model breaks down the text and tokenizes keywords, I compare these extracted keywords with those commonly sought by industry, as outlined by Jobscan. The tool then calculates the frequency of these keywords and the importance of each category, presenting the results to the user in a clear, actionable way.

Challenges we ran into

One of the challenges I ran into was deploying the AI model on the cloud, as my Google Cloud setup initially couldn't deploy my container. Fortunately, I was able to resolve the issue by the end of the day.

Accomplishments that we're proud of

I’m proud that I was able to dive into NLP and gain a deeper understanding of how it works, especially with the tokenization process.

What's next for Resume Reviewer

I hope to further refine and improve the NLP model I'm currently using to provide more accurate resume scores that better align with industry standards.

Built With

• flask
• google-cloud
• nextjs
• spacy
• tailwind
• typescript
• vercel