Data Mining / Data Science Expert (New Energy Vehicle Battery Direction)

Our client is a global fintech that originated as the digital payment engine for e-commerce industries.

Responsibilities

1. Deeply understand charging-pile/battery three-domain data and multi-source user-end data; explore data value for business scenarios; build multi-dimensional feature/tag systems for users, vehicles, charging piles, and batteries.
2. For charging-pile scenarios (value alerts, smart inspection), battery scenarios (assessment, extended warranty, return/exchange, cascade utilization), and EV scenarios (new/used car sales and leasing), build models for user tiering, profiling, lookalike expansion, response/churn prediction, etc., to support operations, marketing, and targeting.
3. Build predictive models for battery SOH/RUL (State of Health / Remaining Useful Life) and vehicle LTV, identifying migration/churn risk to support product and decision-making.
4. Own A/B test design, causal inference, and ROI attribution analysis; quantify the impact of operational initiatives; build and validate pricing models and online effectiveness.
5. Fuse mining algorithms with operational decision-making, pushing data from insight to application (operations, evaluation/pricing, product-operations integration, and data productization).
6. Strong business understanding and team collaboration ability; results-oriented with strong stress tolerance.

Requirements

1. Bachelor's degree or above in Computer Science, New Energy Batteries, Statistics, Mathematics, AI, or a related field; 5+ years of data mining/data science experience; end-to-end data exploration, modeling, and business deployment experience preferred.
2. Deep understanding of the charging-pile/battery user data ecosystem; grasp of the full data landscape and interrelationships across key business scenarios; able to precisely identify core value points, key features, and value-mining opportunities.
3. Solid theoretical foundation in statistics and data mining; familiar with common ML libraries (Pandas, NumPy, Scikit-learn); proficient in Python and SQL; familiar with big-data frameworks (Hadoop, Spark, ODPS).
4. Familiar with user tiering, marketing attribution models, and auto finance/insurance-related data analysis methods; understands customer ecosystems and business operations.
5. Strong business understanding and teamwork; results-oriented with strong stress tolerance.