CRE- Data Scientist

Overview

Work with raw, structured, and unstructured data to perform data cleaning, transformation, and feature engineering.

Prepare high-quality datasets for advanced analytics, machine learning, and forecasting use cases.

Collaborate with cross-functional teams to gather, validate, and understand business and data requirements.

Demand Forecasting and Predictive Analytics

Design, develop, and deploy demand forecasting models using historical sales, pricing, promotions, seasonality, and external factors.

Apply time-series and machine learning techniques (e.g., ARIMA, Prophet, regression, tree-based models, deep learning) to improve forecast accuracy.

Evaluate and monitor forecasting performance using appropriate metrics and continuously refine models to support business planning and decision-making.

Model Development, Deployment, and Monitoring

Build, maintain, optimize, and scale machine learning models, including recommendation engines, in FMCG or consumer goods environments.

Ensure high availability, accuracy, and low-latency performance across platforms.

Continuously enhance models using advanced ML techniques such as collaborative filtering, content-based filtering, matrix factorization, hybrid recommender systems, and graph-based approaches.

Collaboration and Communication

Collaborate with product, marketing, and engineering teams to integrate forecasting and recommendation models into consumer-facing applications, personalization engines, or B2B retail platforms.

Clearly communicate complex analyses, model outcomes, and business insights to both technical and non-technical stakeholders.

Continuous Learning and Research

Stay up to date with industry trends, emerging tools, and best practices in data science, machine learning, forecasting, and AI.

Continuously enhance skills through training, experimentation, and self-directed learning.

Qualifications

Education and Experience

Bachelor’s or Master’s degree in Computer Science, Statistics, Mathematics, or a related field.

Relevant experience as a Data Scientist in applied business environments.

Technical Skills

Strong proficiency in Python for data analysis, statistical modeling, machine learning, and forecasting (pandas, NumPy, scikit-learn, statsmodels, PyTorch).

Hands-on experience in demand forecasting and predictive modeling.

Experience developing recommendation systems and graph-based algorithms (e.g., GraphSAGE).

Strong understanding of model evaluation metrics for both forecasting and machine learning.

Hands-on experience handling large-scale datasets using Azure Databricks and Azure Cloud (mandatory).

Solid knowledge of statistical analysis and data visualization tools.

Problem-Solving

Ability to translate complex business problems into analytical and forecasting frameworks and deliver data-driven solutions.