close



PROP-VALUE : Web Platform That Estimates The Value Of Properties Using Customer-entered Metrics And Microservice Architecture.



Domain :

SRE, AI/ML

started :

01 January 2018

completed :

30 January 2021

As a Software and Machine Learning Engineer on this dynamic project, I was entrusted with pivotal responsibilities that encompassed both software development and machine learning implementation. My contributions played a critical role in shaping the success of our innovative property valuation platform.

  • Implemented microservice architecture to modularize functionality and ensure scalability.
  • Developed a web platform using Java and Spring Boot framework to estimate the value of properties online.
  • Utilized Eureka for service registry, allowing seamless discovery and registration of microservices.
  • Introduced Kafka for streaming and messaging, enabling real-time data processing and communication between different components of the system.
  • Used Ribbon for client-side load balancing, ensuring efficient distribution of requests across multiple instances of microservices.
  • Collaboratedwith the frontend team to define APIs and ensure smooth integration between frontend and backend systems.
  • Conducted thorough testing and debugging to ensure the accuracy and reliability of the property valuation algorithm.
  • Workedclosely with the product team to gather requirements, provide technical insights, and ensure alignment with the project goals.
  • Followed Scrum methodology and employed Atlassian Jira, Confluence, and Bitbucket for project management, sprint planning, issue tracking, and code management.
  • Led development of a cutting-edge property valuation platform, yielding 15% higher accuracy compared to traditional methods.
  • Implemented microservice architecture to modularize functionality and ensure scalability.
  • Developed a web platform using Java and Spring Boot framework to estimate the value of properties online.
  • Collaborated with data scientists to implement advanced ML algorithms, reducing prediction errors by 20% using regression and gradient boosting techniques.
  • Conducted rigorous testing and validation, achieving a 95% confidence level in valuation predictions.
  • Technologies Used: Java, Spring Boot, MongoDB, Eureka, Kafka, Ribbon, Microservices, MySQL, Jira, Confluence, Bitbucket, Scrum