Data Scientist

Roles & Responsibilities
- Work with stakeholders throughout the organisation to identify opportunities for leveraging internal/external data to drive business solutions.
- Develop a DS use case roadmap for a problem area or capability for the business.
- Mine and analyse data from company databases to drive optimization and improvement of product.
- Develop end to end Credit Risk scorecards/models ranging from applications to behaviour to collections scorecard using techniques such as linear model/regression, logistic regression, random forest, boosting/bagging trees, dimensionality reduction algorithms.
- Work as the data strategist, identifying and integrating new datasets that can be leveraged through our product capabilities and work closely with the engineering team to strategize and execute the development of data products.
- Enhance data collection procedures. Processing, cleansing, and verifying the integrity of data used for analysis.
- Run data exploration to understand relationships and patterns within the data, develop data visualisation to represent the relationships identified from data exploration.
- Data mining using state-of-the-art methods. Selecting features, building and optimizing classifiers using machine learning techniques.
- Refine and deepen understanding of the algorithmic and inferential aspects of statistical analysis. Evaluate new algorithms from latest research and develop intuition about the problems for which they are likely to improve the state of the practice.
- Build training pipelines for the production environment. Develop and execute on a plan for continuous iteration and refinement of a new model.
- Provide inputs for design, quality assurance parameters and support implementation for the model in an online environment.
- Provide inputs and determine infra requirements and infra management for model deployment.
- Lead debugging of data pipelines and model behaviour in production environment.Develop dashboards to enable easy tracking and communication of model impact.

Required Skills & Qualifications
- We’re looking for someone with 2 ~ 5 years of experience manipulating data sets and building statistical models, with a Bachelor’s/Master’s/PhD degree in Statistics, Mathematics, Computer Science or another quantitative field, from any of the top-tier colleges. 
- Strong problem solving skills with an emphasis on product development.
- Excellent written and verbal communication skills for coordinating across teams.
- Good applied statistics skills such as distributions, statistical testing, regression.
- Good scripting and programming skills in Python, pyspark and SQL.
- Excellent understanding of machine learning techniques and algorithms, such as k-NN, Naive Bayes, SVM, Xgboost, Decision Forests, artificial neural networks and their real-world advantages or drawbacks. Knowledge of deep learning techniques is a plus.
- Experience with common data science toolkits such as NumPy, Pandas, Scikit-learn, TensorFlow, Keras etc.
- Experience with data visualisation tools such as Tableau.
- Experience in credit, risk, or collections management (e.g., Application Scorecard, Behaviour Scorecard, Collection Scorecard, Loan Pricing, Propensity Model, Cross-Sell Model) is a strong plus.
- Experience with NoSQL databases such as MongoDB, Cassandra, HBase is desired.
- Experience with distributed data/computing tools like Map/Reduce, Hadoop, Hive, Spark is a big plus.
- Hands-on experience with cloud computing and big data platforms (e.g., AWS S3, SageMaker, Athena, and Databricks) would be preferred