Vp - Risk Analytics (Leading Fintech)

Role Will Be Responsible For :

- Leading And Managing A Team Of Data Scientist And Data Engineers, Leading The Projects In Artificial Intelligence And Data Science Space

- Translating Use Cases To Analytics Agenda, Including Data, Approach And Validation Strategy

- Leading Multiple Projects With Diverse Scope And Complex Business And Technical Challenges Across Several Business Units And Functions

- Developing Best Practices For Data Science, Considering The Full Analytical Lifecycle

- Developing Guidelines For The Evaluation Of New Analytical Tools And Platforms

- Acting As An Evangelist For Data Science In The Enterprise Community

- Identifying Business Opportunities And Solutions

- Deriving And Implementing Best Approaches For Predictive And Prescriptive Analytics

- Acquiring Or Develop Innovative Methodologies

- Leading And Guiding Analytics Projects Across Business Groups

Desired Profile :

- Looking For Candidates With Extensive Experience Leading, Coaching, And Developing People And Robust Teams

- Must Have Knowledge Of Most Of The Following Quantitative Fields Like Machine Learning, Advanced Statistical Analysis &Amp; Modeling, Deep Learning, Causal Inference &Amp; Program Evaluation, Reinforcement Learning, Behavioral Economics, Design Of Experiments, Multi-Objective Optimization, Decision Theory, Bayesian Statistics, And Network Science Etc.

- Must Have Strong Data Proficiency, Exploratory Data Analysis, Data Visualization, And Story Telling Skills

- Must Have Knowledge Of Well-Designed Experiments And Statistical Analysis Concepts

- Must Have Knowledge Of Big Data Technologies Such As Cloud Computing, Gpu Computing, Hadoop, Spark, Mapreduce Or Related Massively Parallel Processing Technologies

Risk Analytics :

1. Development &Amp; Validation Of Application Scorecards For Various Loan Segments

2. Controlling Business Attrition Using Commercial Bureau Triggers

3. Risk Monitoring Of Loan Portfolio

4. Monitoring Of Loan Portfolio:

5. Delinquency Analysis

6. Flow Rates

7. Vintage Curve

8. Attrition Analysis

9. Exploring Multi Bureau Usage For Credit Underwriting In Sme/Retail Segment

Sales / Marketing Analytics

Using Statistical &Amp; Predictive Modelling Techniques Like Linear Regression, Logistic Regression, Decision Trees, K-Means Clustering Etc. For Various Areas Of Asset Analytics Like :

1. Customer Acquisition And Attrition

2. Portfolio Level Customer Segmentation

3. Propensity For Cross-Holdings, Product Per Customer, Next-Best Product

4. Identifying Potential Customers For Up-Migration To Higher Customer Segment

5. Development Of X-Sell Programs

6. Generating Analytics Based Leads Using Commercial Bureau Data

7. Loan Approval Scorecard

8. Risk Based Pricing Model