MAJOR Project
JOB Recomendation - Neo4j graph database
OVERVIEW
This project entails a job recommender system utilizing a Neo4j graph database. It employs FP Growth to discern frequent patterns between skills and domains, and link prediction algorithms (Adamic Adar, Common Neighbors) for job recommendations. Python, Cypher, Neo4j, and NetworkX form the tech stack.
Contribution
- Developed a graph-based job recommendation system using Python, Cypher, Neo4j, and NetworkX.
- Leveraged Neo4j graph database to manage and analyze data effectively.
- Utilized FP Growth algorithm to generate frequent patterns between skills and domains.
- Employed link prediction algorithms such as Adamic Adar and Common Neighbors to recommend jobs.
- Collaborated on the project’s GitHub repository and contributed to the architecture design
JD & Resume Graph
Neo4j Graph DB
Architecture
Year
2022
Client
College Project
Services
Recommender System
Skills
Python, Neo4j Graph DB, NetworkX
Description
- The project revolves around a job recommender system that uses a Neo4j graph database.
- The system generates frequent patterns between skills and domains using the FP Growth algorithm, a method used for frequent itemset mining and association rule learning over transactional databases.
- The recommendation process utilizes link prediction algorithms, specifically Adamic Adar and Common Neighbors.
- These algorithms predict the likelihood of the existence of a link between two nodes, in this case, the job seeker and the job.
- Python, Cypher, Neo4j, and NetworkX are the main technologies used in this project