Sam John

AI Researcher

Bengaluru, Karnataka, India4 yrs 1 mo experience

Highly Stable

Key Highlights

Expert in data-driven solutions for retail and customer insights.
Proven track record in developing scalable machine learning models.
Strong communicator with cross-functional collaboration skills.

Stackforce AI infers this person is a Data Scientist specializing in Retail Analytics and Customer Insights.

Contact

Skills

Core Skills

Data ScienceBig Data AnalyticsCustomer AnalysisPredictive ModellingMachine LearningPricing AnalysisRetail Domain KnowledgeFinancial AnalysisData Visualization

Other Skills

PySparkPython (Programming Language)SQLFastText embeddingslogistic regressionclassification modelsA/B testingSparkbig data pipelinesdistributed computingClickstream analysiscustomer segmentationdashboardingPricing strategyproduct ranging

About

Data Scientist with 3+ years of experience in customer and retail consultancy, big data analytics and data science. Skilled in PySpark, SQL, predictive modelling, A/B testing and pricing strategies to optimise product performance and customer engagement. Adept at leveraging data-driven insights to drive business growth, cost reduction and improve operational efficiencies. Passionate about developing scalable algorithms, machine learning models, automated solutions and data-driven decision-making frameworks that help in achieving business objectives. A strong communicator with the ability to collaborate cross-functional role and translate complex data into actionable strategies for stakeholders. With a results-driven mindset and a deep analytical approach, I provide consistent delivery of impactful insights and innovative solutions that drive measurable business success.

Experience

4 yrs 1 mo

Total Experience

3 yrs 7 mos

Average Tenure

6 mos

Current Experience

Fractal

Analytics Consultant

Nov 2025 – Present · 6 mos · Bengaluru, Karnataka, India

Dunnhumby

2 roles

Senior Applied Data Scientist

Promoted

Jul 2024 – Nov 2025 · 1 yr 4 mos · Gurugram, Haryana, India · Hybrid

At dunnhumby, I’ve delivered data-driven solutions across pricing, promotion and channel strategy functions. I specialize in processing large-scale datasets using PySpark, SQL and Python, and translating analytical insights into actionable business outcomes. My work integrates analytical precision with business impact, enabling strategic decision-making for customer-driven growth at the leadership level.
Technical Skills & Tools:
Languages: PySpark, Python, SQL
Machine Learning: FastText embeddings, logistic regression, classification models, A/B testing
Data Processing: Spark, big data pipelines, distributed computing
Analytics & BI: Clickstream analysis, customer segmentation, dashboarding
Retail Domain Knowledge: Pricing strategy, product ranging, competitive intelligence
Key Achievements & Impact:
Competitor Impact &Customer Retention Analysis: Led competitor impact analysis for 28 stores affected by regional competition, uncovering customer attrition trends and informing retention initiatives.
A/B Testing at Scale: Designed and implemented an end-to-end A/B testing framework that enabled expansion of pharmacy trials from 7 to over 60 stores, improving market penetration and targeting strategies.
Automated ML Classification: Developed a machine learning pipeline using FastText embeddings and logistic regression to classify new product SKUs with 87% accuracy, significantly reducing manual tagging efforts.
Clickstream & Search Analysis: Explored customer clickstream data to identify browsing and purchase patterns across different times of day/week, which informed personalized marketing and in-store merchandising decisions.
Competitive Pricing Benchmarking: Conducted a detailed pricing and promotions comparison across national competitors, uncovering whitespace and driving optimized pricing strategies across multiple categories.

PySparkPython (Programming Language)SQLFastText embeddingslogistic regressionclassification models+12

Applied Data Scientist

Apr 2022 – Jul 2024 · 2 yrs 3 mos · Gurugram, Haryana, India · Hybrid

Developing and executing impactful projects to drive business objectives in store-ranging merchandising and pricing & promotion divisions.

Pricing AnalysisStore Ranging MerchandisingRetail Domain Knowledge

Earlysalary- instant salary advance for employees

Management Trainee and Decision Analytics

Apr 2021 – Aug 2021 · 4 mos · Pune, Maharashtra, India · Hybrid

During my internship at EarlySalary, I developed a real-time monitoring dashboard using AWS QuickSight to track NBFC performance metrics, enabling data-driven decision-making through advanced data visualization. I also automated ETL pipelines using KNIME, seamlessly integrating data from MySQL, MongoDB, and Athena to facilitate real-time performance analysis. Additionally, I implemented anomaly detection frameworks, enhancing operational efficiency and reducing system failures, which significantly improved system reliability and business continuity.

Data AnalysisMicrosoft ExcelData Visualization

Vinidhan:the student investment fund

Senior Analyst

Mar 2021 – Mar 2022 · 1 yr · Goa, India

As a member of Vinidhan: The Student Managed Investment Fund of GIM, I actively managed an investment fund with real-time exposure to the equity market. I developed a quantitative trading strategy, achieving a backtested profitability of 54% on NIFTY-50 stocks. Additionally, I conducted in-depth industry research on the Power sector, analyzing market trends, regulatory impacts, and investment opportunities to support informed decision-making.

Cost AccountingMicrosoft ExcelFinancial Analysis