핵심 요구사항
- Python/Pandas/NumPy 기반 데이터 전처리 및 ETL 파이프라인 구축
- PostgreSQL(Neon) 데이터베이스 설계 및 연동
- Random Forest 등 회귀 모델 학습 및 특성 분석
- FastAPI 백엔드 및 분석·예측 API 개발
- React 프론트엔드 연동 및 결과 시각화
Required stack
필요 기술
PythonPandasScikit-learnPostgreSQLFastAPIReactNumPyETL
Project brief
프로젝트 내용
Machine Learning Pipeline – Job Market Analytics & Salary Prediction
Created an end-to-end machine learning pipeline for looking at job market data and guessing what salaries might be.
Key Features:
Worked on. Fixed 10,000 or more job-market records using Python, Pandas and NumPy.
Made an automated ETL/data preprocessing pipeline to take care of data cleaning, changing data making it all the same and checking if it is all the same.
Added a PostgreSQL (Neon) database to keep data in a good way and help with machine learning work.
Did analysis of the data. Looked at the features to find what helps predict salary.
Trained a Random Forest regression model to guess salaries.
Found that employee_residence is one of the things to use for guessing salaries.
Built a FastAPI backend with places to get analytics and predictions.
Linked the machine learning backend to a React frontend to show information and results in a way.
Technologies: Python, Pandas, NumPy, Scikit-learn, Random Forest, PostgreSQL, Neon, FastAPI, React, ETL.
This project shows experience, in data preprocessing, machine learning, database integration, API development and full machine learning deployment.
Created an end-to-end machine learning pipeline for looking at job market data and guessing what salaries might be.
Key Features:
Worked on. Fixed 10,000 or more job-market records using Python, Pandas and NumPy.
Made an automated ETL/data preprocessing pipeline to take care of data cleaning, changing data making it all the same and checking if it is all the same.
Added a PostgreSQL (Neon) database to keep data in a good way and help with machine learning work.
Did analysis of the data. Looked at the features to find what helps predict salary.
Trained a Random Forest regression model to guess salaries.
Found that employee_residence is one of the things to use for guessing salaries.
Built a FastAPI backend with places to get analytics and predictions.
Linked the machine learning backend to a React frontend to show information and results in a way.
Technologies: Python, Pandas, NumPy, Scikit-learn, Random Forest, PostgreSQL, Neon, FastAPI, React, ETL.
This project shows experience, in data preprocessing, machine learning, database integration, API development and full machine learning deployment.
지원 기회 분석
지원 전에 볼 것
예상 산출물
- 자동화된 ETL/데이터 전처리 파이프라인
- 학습된 급여 예측 ML 모델
- FastAPI 기반 분석·예측 API 백엔드
- React 대시보드 프론트엔드
매력 포인트
- 기술 스택과 기능 범위가 비교적 명확
- 풀스택 ML 포트폴리오로 활용 가치 높음
확인할 점
- 예산 통화 표기가 혼란스러움($ 기호와 INR 병기)
- 예산 하한($1,500 상당)이 풀스택 ML 파이프라인 범위 대비 낮을 수 있음
- 설명이 이미 완료된 작업 회고처럼 서술되어 실제 요구 범위가 불명확
Client signal
클라이언트 정보
플랫폼에서 상세 정보를 확인하세요.