Data Scientist Store Workload Labor Optimization

TCS is hiring for Data Scientist Store Workload & Labor Optimization

Please share your cv at [email removed]

Industry - Retail

Qualification - Minimum 15 years of regular, full-time education (10 + 2 + 3)

Shift- Night Shift

Job Role-

As a Data Scientist Store Workload & Labor Optimization, you will design, develop, and deploy predictive models and optimization algorithms that directly influence store execution, labor scheduling, and financial performance.

You will bridge the gap between complex operational data (e.g., labor hours, sales execution & performance, task tracking, traffic patterns, and product volumes) and high-impact business outcomes.

Your algorithms will ensure stores have the right associate, performing the right task, at the right time, while maximizing the stores Profit & Loss (P&L) health and customer experience.

Responsibility

A. Store Workload & Effort Analytics

• Task Effort Modeling: Build predictive models to quantify the labor time required for core store activities, including truck unloading, sorting, Planogram (POG) set-ups, pricing changes, and inventory replenishment.
• Workload Forecasting: Forecast weekly and seasonal workload spikes (e.g., peak holiday crafting seasons) based on historical shipment volumes, category mix, and promotional schedules.
• Analyze time-and-motion data to pinpoint operational bottlenecks on the sales floor and in the backroom with respect to Sales Volume and Area.

B. Labor Allocation & Schedule Optimization

• Staffing Curve Optimization: Develop algorithms to generate optimal daily/hourly staffing curves that align with customer foot traffic, transaction velocities, and workload tasks. Assessment of current models vs actual performance.
• Labor Budget Allocation: Formulate mathematical optimization models to distribute regional and district-level labor budgets across individual stores.

C. Store P&L and Financial Analytics

• Labor ROI Modeling: Quantify the financial return on labor investments. Model the relationship between labor spend, customer conversion rates, and overall net sales
• OpEx Optimization: Leverage regression and anomaly detection to analyze store-level Operating Expenses (OpEx) and identify cost-saving opportunities in facilities, waste, and shrinkage.
• Performance Compliance Modeling: Create machine learning models to detect low-compliance stores in real-time (e.g., missed ad sets, late planogram execution, or delayed price audits) using sales patterns.
• Explainability : Translate complex statistical results into intuitive executive dashboards and highly actionable operational recommendations.

Required Qualifications & Skillsets

• Masters or bachelors degree in a highly quantitative field (e.g., Operations Research, Industrial Engineering, Statistics, Applied Mathematics, Data Science).
• A minimum of 3+ years of hands-on data science or operations research experience, Prior experience in retail workforce management (WFM), supply chain planning, or store operations analytics is highly desirable.
• Programming & Scripting: Expert proficiency in Python (specifically libraries like pandas, scipy, scikit-learn, PyTorch or TensorFlow), pyspark.
• Database & Big Data: Advanced SQL mastery; experience with cloud data warehouses like Snowflake, Databricks, or AWS for querying massive, multi-million-row transaction tables.
• Forecasting & ML: Deep understanding of time-series forecasting (e.g., Prophet, ARIMA, XGBoost) and supervised classification/regression algorithms.