Collection Data Scientist (Internal Hiring) (J24484)
  • 招聘類別:
  • 社會招聘
  • 工作性質:
  • 全職
  • 薪資范圍:
  • 招聘人數:
  • 1
  • 發布時間:
  • 2021-07-29
  • 截止時間:
  • 工作地點:
  • 天津市


Duties and responsibilities:
In this role you will be working for the data science team within collection department; Risk management division. The goal of this team is to deliver predictive models to optimize collection processes. Except for modeling, you will be responsible for deployment of collection models, monitoring, regular maintenance, big data involvement.

Our technology stack is built around open source software, particularly Python, Oracle and Hadoop (jupyter notebooks, sklearn, xgboost, PL/SQL, hive, Pyspark, impala).

Key responsibilities:
? Understand and then analyze the business requirement of collection in data science field
? Design and implement predictive models which affiliate the business needs
? Understanding available data sources, exploring and evaluating new ones
? Sample preparation, including data retrieval from a database, data cleaning, encoding, and feature engineering
? Model evaluation and documentation
? Regular monitoring of model and segmentation performance


? Proven track of successful machine learning applications in a business environment
? University graduate, preferably with major in mathematics, statistics, computer science or data science

Required skills
? Solid understanding in statistical theories, methodologies, and concepts, including but not limited to: probability theory, normal distribution, hypothesis testing, regression, clustering, sampling etc.
? Understanding of artificial intelligence and machine learning algorithms and concepts, including but not limited to: heuristics, supervised learning, validation set, overfitting, decision tree, KNN, SVM, logistic regression etc.
? Skills in a major programming language relevant to the field (Python, R, etc.)
? Familiarity with SQL and relational database concepts
? Hands-on experience with building, deploying and monitoring of predictive models in business environment (2+ years)
? Ability to turn idea into algorithm

Nice to have skills
? Fluent English language is advantage
? Experience with machine learning projects in python is a big plus
? Experience with python ecosystem (pandas, sklearn, python built-in data structure, jupyter notebooks) is a plus
? Understanding of Hadoop ecosystem and practical ability to write Hive/Spark queries

©2021  捷信消費金融有限公司   京ICP備05051632號-16 京公網安備 11010802020454號 Powered by