Reemu, data scientist

Reemu

Senior Data Scientist

Bengaluru, India · UTC+5:30 · 13 years of experience

Reemu focuses on turning messy data into tested models and useful decisions.

Request a shortlist

Why this profile fits

Decision-first problem framing

Starts with the decision, target metric, and data limits before choosing a model or analytical method.

Validated modeling

Uses holdouts, experiment design, and error analysis to separate a useful signal from a convincing notebook.

Clear operational handoff

Documents assumptions, monitoring needs, and the path from analysis to a decision or production workflow.

Relevant toolkit

PythonSQLscikit-learnPyTorchdbt

Delivery evidence

Selected work

Hierarchical Demand Forecasting Platform

National grocery retailer

Replaced a manual SARIMAX process with a reconciled hierarchical LightGBM forecast across 40,000 SKUs and 1,200 stores. Cut weighted error from 31% to 18% and freed roughly $9M in working capital while lowering fresh-food waste by 22% within two quarters.

PythonLightGBM

Probabilistic Sales Forecasting for S&OP

Consumer packaged goods manufacturer

Built a Temporal Fusion Transformer producing P10/P50/P90 sales forecasts feeding a monthly sales-and-operations planning cycle. Improved 13-week forecast bias from 12% to under 3% and gave finance defensible revenue ranges, cutting emergency production runs by a third.

PythonPyTorch
View more profile detail →

Relevant experience

Career timeline

Principal Data Scientist, Forecasting

2021–Present

Devlyn (a ViitorCloud company) · Bengaluru, India (Remote)

  • Lead demand and sales forecasting engagements for retail, CPG, and logistics clients, owning models from data contract to production and typically improving forecast accuracy 20% to 40% within the first quarter.

Software Engineer

Sep 2022–Present

ViitorCloud Technologies · Bengaluru, India

  • Built the first end-to-end demand forecasting system for a national grocery client, moving 40,000 SKUs off spreadsheets onto hierarchical LightGBM and freeing about $9M in working capital.

Full Stack Developer Intern

Jan 2022–Sep 2022

iView Labs Pvt. Ltd. · Bengaluru, India

  • Developed weekly sales forecasts for 5,000+ product categories that fed inventory and marketing budgets, improving category-level accuracy 18% over the incumbent moving-average model.

Skill depth

Show experience in context.

VerbalCommunicationDomainUnderstandingProblemSolvingCodeQualitySystemDesignDeliverySpeed
Competency shapeAssessment across the same six dimensions used for every profile.

Relevant experience by skill

Python13 years
SQL13 years
Statistical Modeling12 years
Time-Series Forecasting11 years
scikit-learn10 years
Demand Forecasting9 years
PyTorch6 years
dbt5 years
See the complete skill index

Languages

PythonSQLRScalaBash

Frameworks

PyTorchTensorFlowscikit-learnstatsmodelsProphetPyTorch ForecastingDarts

Libraries/APIs

pandasPolarsNumPyLightGBMXGBoostSciPyPyMCOptunastatsforecastLangChain

Tools

dbtMLflowAirflowGreat ExpectationsDockerGitJupyterStreamlitWeights & Biases

Paradigms

Hierarchical ForecastingProbabilistic ForecastingA/B TestingCausal InferenceBayesian InferenceMLOpsFeature Engineering

Platforms

SnowflakeBigQueryDatabricksAWS SageMakerGoogle Vertex AIKubernetes

Storage

SnowflakeBigQueryPostgreSQLpgvectorRedisAmazon S3

Other

Demand PlanningSales & Operations Planning (S&OP)Inventory OptimizationData StorytellingStakeholder Management

Education

Formal background

Master of Statistics (M.Stat), Statistics

Indian Statistical Institute · 2011–2013 · Specialization in time-series analysis and applied statistics

Bachelor of Science (B.Sc), Statistics

University of Delhi · 2008–2011 · First class with distinction

Credentials

Certifications

SnowPro Advanced: Data Scientist

Snowflake · 2024 · Certified

AWS Certified Machine Learning Engineer – Associate

Amazon Web Services · 2023 · Certified

Communication

Languages

Tamil

Native

Hindi

Fluent

English

Fluent

More examples

Similar Data Scientist profiles.