• Run CRISP-DM projects with a team of 3 data scientists in the following - • Selecting features, building and optimizing classifiers (logistic regression or RF based propensity models) and recommenders using machine learning techniques • Data mining using state-of-the-art methods - Automate scoring using machine learning techniques, build recommendation systems, improve and extend the features used by recommendation and propensity modeling algos • Extending company’s data with third party sources of information when needed • Enhancing data collection procedures to include information that is relevant for building analytic systems • Processing, cleansing, and verifying the integrity of data used for analysis and perform deep EDA (we create our own training data for our models) • Doing ad-hoc analysis and presenting results in a clear manner • Creating recommended and propensity models and tracking of its performance especially to compensate for concept drift

• Onboard a hands-on SME in leveraging big data tech to solve complex data issues. • Spend almost half of time with hands-on coding. • Involves large scale text data processing, event driven data pipelines, in-memory computations, optimization considering CPU core to network IO to disk IO. • Use cloud native services in AWS and GCP.

• Design, train, validate, and deploy machine learning and deep learning models in production environments with big data. • Implement advanced anomaly detection and pattern recognition techniques to identify irregularities, fraud, operational risks, or atypical behavior in the data. • Execute A/B testing and statistical experimentation to validate hypotheses, measure impact, and optimize information analysis products. • Collaborate with cross-functional teams (product, engineering, business, tax/accounting) to translate needs into data science use cases. • Ensure data quality through pipeline cleaning, validation, orchestration, and monitoring processes. • Develop and maintain technical documentation, metrics dashboards, and model performance reports. • Propose new solutions based on predictive models, advanced analytics, and generative AI techniques that add strategic value.

• Develop and maintain innovative models for asset valuation. This requires thorough statistical analysis of the underlying data and understanding of the various macroeconomic factors and risk factors that impact prices and liquidity in the real estate market. • Develop models for portfolio management purposes such as value forecasting or market risk segmentation. • Closely provide regular ongoing model performance assessments and enhance existing models. • Develop analytical tools to support other teams • Working with the technology team, drive initiatives to enhance data capabilities and streamline infrastructure. • Work closely with engineers/data infrastructure team in designing useful data attributes. • Perform exploratory analysis and make recommendations on improving current data models, decisioning frameworks, etc. • Refactor existing analytic solutions to improve scalability.