Jun 2021 – Jul 2024 · 3 yrs 1 mo · Hybrid

• Last Mile Science
• > Formulated psychometric analysis approach for improving classification accuracy of Claude LLM models. Applied the tech-stack to categorize more than 500 delivery service provider (DSP) insurance claims into 10 categories using agent written incident notes achieving 98% accuracy.
• > Projected Station-DSP pair route capacity using XGB-Linear model for long-range capacity planning using over 500 features specific to DSP performance, station volume, network health, reliability, vehicles, drivers etc. Enhanced ability to predict for New-DSP launches, Transfers, Pop-ups, Pinnacle achieving 500 bps improvement over baseline model saving $70M.
• > Optimized long-range capacity planning decisions using mixed integer linear programming coding in Gurobi and Xpress solvers to generate target deployment plans for stations. Using conditional indicator constraints, calculated temporal aspects of capacity utilization and generated eligible DSP, role and station mapping to make deployment decisions among new-DSPs, Pop-Ups, Pinnacle and Transfers across the North America region for peak planning. Using chance constraints, added the fluctuations in
• volume signals allowing planners to do scenario analysis at station level and save $200M in planning costs.
• > Modeled XGBoost classification algorithm for internal safety risk evaluation models using telematics data, weather data and workplace conditions to build decision mechanisms for targeted coaching aimed at reducing Accidents per Million Miles. Using a minimum detectable effect of 2% and statistical power of 90%, implemented an experiment to observe cost savings of $16M.
• > Estimated effectiveness of existing safety programs using generalized synthetic control causal inference framework by calculating counterfactual outcomes and performing gap analysis to estimate impact on safety metrics through training period. Summarized results using Average Treatment Effect for Treated Units (ATT) vs time of treatment.

Jan 2020 – May 2021 · 1 yr 4 mos · Hybrid

• Devised customer service associate personalized coaching models using probabilistic prediction of successful delivery rate on customer contacts using tree based classifiers. Pioneered performance vs mix contribution index to bridge KPI variance summarizing results using Tableau Dashboards reducing manual effort by 50% for 726 users savings $7M in improved efficiency.

Aug 2019 – Dec 2019 · 4 mos · McLean, Virginia, United States · On-site

• Pharmaceutical client
• > Time Series Forecasting of Call Volume Data (Insight Studio): Developed multivariate time series forecasting model of call volume data for pharmaceutical company using SARIMA-X and XG-Boost models using data-distribution based features, time based features, holidays and call center capacity constraints. Visualized feature importance using partial dependence plots, scatter plots and SHAP values to improve model explainability achieving average improvement of 210 bps over baseline model.
• Call Intent Classification
• > Classified agent notes into actionable intents for improving call routing using NLP techniques, supervised classification using LDA and unsupervised classification using Spectral Ensemble Clustering. Vectorized text using TF-IDF vectorization.
• Talent group: Analytics and Cognitive
• Sub-capability: Applied AI
• Competency: Strategy and Operations
• Team: InsightStudio

May 2016 – Mar 2018 · 1 yr 10 mos · Gurugram, Haryana, India · On-site

• Relevancy based personalization of emails, tasks and chats
• > Designed communication and collaboration tool “Eazespot” showing most relevant tasks, chats and emails on a single platform for 800 live beta users. Using bi-grams labeled emails into tasks, meetings, to-do’s linking them with a calendar to show relevant information on a single UI – Ease-Today.

Jul 2015 – Apr 2016 · 9 mos · Gurugram, Haryana, India

• > Customer Promise Engine: Build random forest classification algorithm on R, taking delivery intervals as 0-2, 3-5, 4-7, 8 or more. Input features included range of delivery time between origin and destination zip codes, holiday features and time related features achieving average accuracy of 94%, average improvement of 2600 bps over baseline model.
• > Warehouse Velocity Planning: Identified fast moving inventory items based on sales from last 15 days and created a software integration which pulls these fast moving items and prepares a list for operations team to predict quantity of sale on the following day. Implemented fast moving zones near invoicing station to reduce order processing time.
• > Increasing Active Sellers: Active sellers were defined as the number of sellers having orders more than 5 in a month. Identified the buckets in which active seller percentage was less than 3%, using hypothesis testing changing independent variables to identify the correlations and increased the percentage from <3% to greater than 15%.

May 2014 – Jun 2014 · 1 mo · Uttarakhand, India

• Forecast Spare Parts Inventory and defined ROP/ROQ:
• Developed exponential smoothing model for forecasting spare parts demand by analyzing past consumption patterns
• Reduced Inventory holding levels by 10% translating savings of 80,00,000 INR
• Human Performance Index
• Developed a mathematical unbiased formula for calculating the performance of maintenance workers using indicators like hours of work, hours input in task A, B, C etc. The metric would rank different workers based on their historical performance and was used by HR to reward top workers to create a healthy competition among the factory workforce.

Mar 2013 – Mar 2014 · 1 yr · IIT Roorkee

• Lead a team of 20 students.
• Designed and Fabricated Robots using Solid works for Robocon 2014.
• Marketing head and collected sponsorship from alumni.
• Secured AIR 5th with Best Aesthetic Robot Award.

Jul 2012 – Mar 2013 · 8 mos · IIT Roorkee

• Contributed in design and Fabrication of Robots using solid works.
• Collected sponsorship from alumni for Robocon 2013.

Apr 2012 – Mar 2013 · 11 mos

• Organizing lectures and workshops on robotics.
• Organizing various Techno-creative competitions.