HK – O&T – Senior BigData Modeler

Full Time
Junior (less than 3 years)

Job Description

HK – O&T – Senior BigData Modeler

Location: APAC-HKG-Hong Kong-Hong Kong

  • Work with a small but focused BigData analytics team to conduct data mining in Hadoop ecosystem across a big variety of large datasets, understand fraud/risk elements and pattern, and design corresponding analytical solution
  • Research and develop machine learning/deep learning models on banking transactional data, staff behavioral data, and more importantly, on Natural Language Process and Image Processing domain to deliver state-of-the-art surveillance solution to the franchise
  • Be responsible for UAT testing, MIS reporting and documenting the solution designed to meet the risk and process control standard of Citi
  • Be responsible for knowledge transferring, coaching on advanced analytics and generalize the solution to all the regional internal fraud teams within Citi via liaising with corresponding stakeholders across the globe
  • Be partner with technology function in Citi for data management including new data acquisition, data model design, and data quality investigation in Hadoop ecosystem


  • Prefer Master/PhD in Mathematics/Statistics/Computer Science/Engineering/Any other major that is able to demonstrate solid technical and analytical skills.
  • 2+ years’ working/research experience in data mining/machine learning
  • Experience on Fraud/Anomaly Detection/Risk Management is a plus
  • Proficient in data query language: SQL or NoSQL. Experience on Hive/Pig is a plus
  • Proficient in using R to conduct data mining, modeling; Python proficiency is a plus
  • Basic data mining techniques – principle component analysis, factor analysis, hypothesis testing, clustering etc.
  • Basic Text Mining – tokenization, lemmatization, parsing, semantic analysis; Knowledge on Natural Language Processing/Image Processing is a plus
  • Knowledge and project experience on supervised machine learning models – Regression, Logistic, Neural Network, SVM, Bayesian Network; Un-supervised machine learning models - Nearest neighbor, K-means. Knowledge on Deep Learning is a plus
  • Proficient in both spoken and written English. Fluency in other languages is a plus
  • Focused and proactive; Open-minded and creative; Matured and teamwork
  • Be ready for and willing to travel or short-term oversea assignment

Technical Skills

  • Apache Hadoop
  • Data Management
  • Data Mining
  • Data Modeling
  • Machine Learning
  • Mathematics
  • Python
  • R
  • Research and Development
  • SQL
  • Statistics
  • Text Mining