.png)
Letting Data Speak!
Case Study
AI-Powered Resume-Job Matching Engine
About the Client
A leading AI-powered Job portal in India
Challenge
The client faced the challenge of automatically matching over 1 million candidate resumes to 50,000 job descriptions using an AI algorithm. They needed an efficient system to create personalized job recommendations for candidates and streamline the resume screening process for recruiters.
Key Results
Developed an algorithm that successfully matched top candidates to job descriptions from a pool of 1M+ resumes
Created personalized home pages for candidates, showcasing top matching jobs based on their resumes
Improved recruiter efficiency by 80% by providing top matching resumes for each job opening in the recruiter dashboard
Solution
JashDS implemented a sophisticated matching algorithm using two technical approaches:
Sentence-to-sentence matching:Extracted sentences from resumes and job descriptions Converted sentences into embeddings using a BERT model Matched embeddings using a fast nearest-neighbor approximation algorithm (HNSW) Created a matching score for each resume-job pair based on the embedding similarities
Collaborative filtering-based approach (not implemented in production):Identified user interest in jobs based on application history Utilized a collaborative filtering-based deep learning algorithm to recommend jobs This approach was not implemented due to limitations with newly uploaded resumes and created jobs
The sentence-to-sentence matching approach was chosen for production, enabling the creation of:
Customized home pages for candidates with top matching jobs
A recruiter dashboard showing top matching resumes for each job opening
Technologies Used
BERT (Bidirectional Encoder Representations from Transformers)
HNSW (Hierarchical Navigable Small World) algorithm
Python
Deep Learning frameworks (e.g., TensorFlow or PyTorch)
Natural Language Processing (NLP) tools
Big Data processing technologies (e.g., Apache Spark)
Other Case Study Items
AI Model for Retail Shelf Monitoring
JashDS revolutionized retail shelf management for a major grocery chain by developing an AI-powered real-time monitoring system. The solution utilized advanced computer vision techniques and deep learning models to detect out-of-stock and misplaced products, significantly improving inventory accuracy and enhancing the customer shopping experience while reducing manual labor costs.
AI-Driven Candidate Screening Revolution
JashDS revolutionized a company's hiring process by developing a GenAI-powered candidate screener that reduced time-to-hire by 50% and improved hiring outcomes. The solution leverages advanced language models to conduct dynamic, role-specific interviews, automatically generating and adapting questions based on job descriptions and candidate responses.
AI-Powered Tyre Dimension Extraction System
JashDS developed an AI-powered computer vision system for a leading automotive e-commerce platform, enabling accurate extraction of tire dimensions from images. The solution, which increased conversion rates by 25% and reduced customer support inquiries by 80%, utilized advanced technologies such as YoloV8 for instance segmentation and custom-designed augmentation techniques to simplify the online tire purchasing process.