Mar 2021 – Jul 2022 · 1 yr 4 mos · New Delhi, Delhi, India · On-site

• I primarily work on time series forecasting / modeling and mathematical programming optimization problems such as
• Monthly demand forecasts for production planning
• Daily demand forecasts for logistics planning
• Vehicle routing optimization, journey planning at scale
• Dynamic order-truck matching (knapsacking + bin-packing)
• Energy-use minimization
• Mixing of raw material to achieve desired concrete compressive strength while minimizing material cost

Jan 2020 – Mar 2021 · 1 yr 2 mos

• ★ Driving Behaviour Based Insurance:
• Built driving behavior profiles for insurance by performing data cleaning in PySpark on AWS EMR, EDA, anomaly detection, and feature engineering computing events of harsh acceleration, braking, over-speeding, seat belt usage, driving time, road type, and used past accident and workshop repairs data. Trained hierarchical clustering model to classify vehicles into different risk categories, which is used to calculate insurance premium discounts.
• ★ Set Up Data Lake and Layered Data Architecture:
• Architected a unified platform for data analysis by setting up a multi-layer architecture integrating vehicle IoT data, CRM, Workshops repair datasets on AWS and IBM Cloud. Setup Spark jobs for incremental data load into data lake
• ★ Dealer Management System Analysis:
• Identified customer pain points by analyzing vehicle repairs data finding patterns in automotive components that require frequent repair and maintenance

Jul 2017 – Sep 2020 · 3 yrs 2 mos

• As a Data Scientist, my work includes:
• ★ Set up AWS data lake, perform data discovery & profiling, project feasibility on datasets generated over 4 decades
• ★ Develop efficient & scalable scripts for cleaning of IoT data collected from Suzuki Connect telematics unit
• ★ Enable data-driven decisions for customer research from vehicle ownership, usage patterns, and maintenance attitude on data sourced through multiple channels
• ★ Developed Python package for distributed vehicle data analysis to reduce development time using PySpark
• ★ Perform vehicle health prognostics by modeling various parameters from vehicles and their service history
• ★ Build proofs-of-concept for Advanced Driving Assistance Systems (ADAS).
• ★ Improved efficiency and reduced manpower requirement in analyzing vehicle testing results from R&D labs of vehicle testing teams by creating dashboards and automated reports
• ★ Reduced ECU validation time by 60% by creating an automation framework for rigorous functional testing of Body Control Module (BCM) on dSPACE Hardware-In-Loop (HIL) testing systems.
• ★ Reduced CAN diagnostic test duration of BCM by 95% by automating on Vector Informatik software stack.
• ★ As an Electromagnetic Compatibility (EMC) Test Engineer, my key responsibilities included:
• New Model Development Testing:
• ⠀• Execute EMI / EMC tests on Maruti Suzuki models as per AIS-004 (3) regulations and Suzuki Engineering Standards
• ⠀• Perform data analysis on observations and reporting of results to design teams
• ⠀• Consultation to all design teams to ensure good EMC performance of electronic components
• ⠀• PROJECTS: Maruti Ertiga, Maruti Vitara Brezza, Maruti SCross Maruti Ciaz, Maruti Ignis, Maruti Baleno, Maruti WagonR, Maruti Eeco, Maruti Alto, Maruti Super Carry, All BS VI models, and more

Jul 2016 – Jun 2017 · 11 mos

• As a recruit to the organization,
• ⠀• Developed skills in CAN bus, ECU software, HILS, and EMI-EMC testing
• ⠀• Underwent two months of rotational training across all verticals- Engineering, Production, Supply Chain, Sales and Marketing, Logistics, Spare parts & Accessories divisions
• ⠀• 3 months of on-job training in Production- Managed production line that produces engine camshafts for Maruti Celerio and Super Carry
• ⠀• Skill-up training programs on MATLAB, Siemens NX, capital and revenue budget planning.
• Activities included:
• ⠀• Project on automation of vehicle CAN functional testing on HILS
• ⠀• Project on automation of vehicle CAN diagnostic testing using software stack from Vector
• ⠀• Support to Telematics team for driving behavior analytics
• ⠀• ECU software re-flashing

Jun 2016 – Jul 2016 · 1 mo · Gurgaon, India

• Contributed to building a time-series production model (using ARIMA, Holt Winters) for predicting ATM transactions for all leading banks across India.
• Language / Frameworks: R, SQL

Jun 2015 – Jul 2015 · 1 mo · Gurgaon, India

• PROJECT: MSIL Catalogue
• MSIL Catalogue was an application for the Windows Phone platform published to the Windows Store.
• The app showcased the entire range of cars from Maruti Suzuki India Limited, listed features of the cars across variants, and prices for different Indian cities, scrapping data from the company's official website.
• (The app is no longer listed on the Windows store)

Sep 2014 – Jun 2016 · 1 yr 9 mos

Aug 2012 – Jun 2016 · 3 yrs 10 mos