Sr. Data Scientist

Must Have Skills:

• Python / R
• Experience in risk scorecards, predictive modelling, machine learning.
• Experience in Univariate and Multivariate Regression, Generalized Regression Modelling, Time series forecasting.

Key Results Areas

• Data mining and identification of trends
• Communication of trends and insights to stakeholders
• Development of scorecards & predictive models

Responsibilities

• understand a business problem & translate into statistical one is a must.
• He/she should be able to decide on the best modeling/analysis techniques and provide actionable insights/ model algorithms to the business.

Model development & Deep-dive Strategic Analysis:

• Data extraction: Extract data from appropriate sources. Require knowledge of databases.
• Data processing: Perform complex data processing (e.g. merging, sorting, data transformations).
• Profiling and analysis: Combine in-depth business knowledge, insights, and techniques such as data visualization, cross-tabs, statistical tests, and data mining techniques to identify risk segments, behavioral trends, product preferences, up-selling, cross-selling, and retention opportunities
• Model development: Apply standard and cutting-edge techniques (statistical modeling, data mining, predictive analytics, machine learning, optimization) to identify drivers of a business metric. Compare techniques using validation to arrive at the best model.

Model scoring and business applications of modeling/analytics:

• Insert developed models into the scoring process
• Improvise the models based on feedbacks from scoring process

Communication, Coordination & Presentation:

• Work with a consultative mindset to gather requirements from other team professionals to identify the right requirements.

Skills:

• Extensive experience of statistical tools e.g. R, Python, VBA, Excel etc.
• Experience in statistical modelling using Univariate and Multivariate Regression, Generalized Regression Modelling, Time series forecasting, Non-Parametric methods, Logistic Regression, Survival Analysis, Factor Analysis, Clustering, CART, Decision Trees, CHAID, Linear Optimization, Hypothesis testing, Boosting Techniques, Factor Analysis, Scorecard Development etc
• Experience in risk scorecards, predictive modelling, machine learning etc.
• Ability to extract data from databases, clean and prepare for modelling.