Kshitij Ranjan
Data Scientist
Amsterdam
Summary
Professional data scientist with strong background in statistical analysis, machine learning, and data visualization. Skilled in Python, R, SQL, and various data processing tools, with focus on delivering actionable insights using machine learning and AI. Known for collaborative approach, adaptability, and consistently achieving impactful results in dynamic environments. Recognized for problem-solving abilities and innovative thinking in leveraging data to drive business decisions.
Overview
7
7
years of professional experience
Work History
DATA SCIENTIST, GLOBAL SCM - ADVANCED ANALYTICS
ADIDAS INTERNATIONAL B.V
06.2022 - Current
- Designed a centralized DC resource recommendation solution which increased DC efficiency by 10% through near realtime scenario-based resource recommendation, using PuLP linear programming
- Developed a high-accuracy shipping forecast leveraging LightGBM, Prophet and MLOps, achieving 80%-95% accuracy across different markets
- Launched DC Productivity Cockpit, enabling stakeholders to monitor and manage DC performance in real-time, leading to 16% reduction in decision-making time
- Technology used: Spark, Python, PySpark, Time Series, Linear Optimizer, Power BI, Databricks
SENIOR DATA SCIENTIST
ENQUERO GLOBAL LLP.
09.2021 - 04.2022
- Designed an Anomaly detection framework, using isolation forest, that increased the Data Quality standards by 12% along with performing root-cause analysis (using Causal Inference and A/B Testing) that led to reduced mean time to resolution by 40 %
- Performed fast-seller analysis, leveraging K-means clustering and XGBoost regression to identify 6% more high-demand articles pre-release, preventing a potential demand loss of 10K units (~$1.2 million) during the Spring-Summer season
- Led a 6-member team to productionalise transactional and profitability datasets across markets by implementing industry-standard ETL processes leveraging Spark SQL and databricks, which lead to 18% drop in data storage costs
- Technology used: Spark, Isolation Forest, Causal Inference, A/B Testing, K-Means clustering, XG Boost
TRAINEE DECISION SCIENTIST
MU SIGMA INC.
08.2018 - 09.2021
- Productionalised an 88% accurate customer churn prediction model leveraging XG Boost and Principal Component Analysis, empowering sellers with actionable insights to proactively address at-risk service accounts, resulting in more targeted retention strategies improving renewal rates by ~21%
- Developed a custom Named Entity Recognition model using spaCy, automating vendor catalog creation by extracting critical information from Statement of Work documents and PDFs, streamlining procurement processes and enhancing data accessibility
- Implemented robust data engineering pipelines to ingest backorder data via REST APIs, automating end-to-end backorder cancellation processes that eliminated manual intervention. This reduced errors and accelerated operations by 60%, significantly enhancing overall supply chain efficiency
- Technology used: R, Microsoft SQL, Logistic Regression, Principal Component Analysis, Power BI
Education
Bachelor of Engineering - Electronics And Telecommunication
Manipal Institute of Technology
Manipal 04.2001 -
Skills
Statistical regression analysis
Random forest modeling
Machine learning
XGBoost model development
Proficient in LightGBM
Deep Learning
Classification modelling using Logistic Regression, Decision Tree
Time Series Forecasting using ARIMA
Databricks
SQL databases
Python programming
PySpark and Spark SQL
PuLP
GUROBI
Model Deployment
ML Ops and pipelines
PowerBI
Timeline
DATA SCIENTIST, GLOBAL SCM - ADVANCED ANALYTICS
ADIDAS INTERNATIONAL B.V
06.2022 - Current
SENIOR DATA SCIENTIST
ENQUERO GLOBAL LLP.
09.2021 - 04.2022
TRAINEE DECISION SCIENTIST
MU SIGMA INC.
08.2018 - 09.2021
Bachelor of Engineering - Electronics And Telecommunication
Manipal Institute of Technology
04.2001 -