Data Scientist / Statistician (model Developer)

Capital One Capital One · Banking · Nottingham, United Kingdom

Develop and maintain machine learning models for underwriting in the financial services market, focusing on feature engineering, insight generation, and handling various data types including sequential and multi-modal data. Requires strong statistics, ML, Python, and Model Risk Management experience.

What you'd actually do

  1. Develop and maintain the machine learning models which define our competitive advantage in the financial services market.
  2. Explore and evaluate data, using advanced feature generation and categorisation techniques, in order to stay at the forefront of innovation.
  3. Analyse tabular and non-tabular data, such as text, logs, or time series, to produce powerful new insights.
  4. Consult on complex statistical test design, to efficiently learn our way into new areas of the market.
  5. Use a combination of business acumen, coding and statistical skills to navigate large amounts of data and extract actionable solutions, working cross-functionally to support key business initiatives and drive sustainable growth.

Skills

Required

  • probability
  • statistics
  • machine learning
  • feature extraction
  • large data set manipulation
  • deep learning models
  • sequential data
  • Open Banking or Credit Bureau data
  • multi-modal data
  • Python
  • Model Risk Management
  • technical documentation
  • coding best practices
  • validation
  • ongoing monitoring

Nice to have

  • new languages and technologies

What the JD emphasized

  • Model Risk Management
  • feature engineering
  • insight generation
  • underwriting

Other signals

  • develop and maintain machine learning models
  • feature engineering
  • insight generation
  • underwriting
  • Open Banking or Credit Bureau data
  • Model Risk Management