• Performed manufacturing optimization by deploying linear programming (LPP), seasonality trends and demand forecasting to ensure the optimal tonnage of organic chemicals product portfolio is produced on a month-to-month basis.• Strategized sourcing the type and quantity of raw materials by featuring seasonality trends and annual demand forecasting to minimize the procurement and cost of the key materials, leading to, an average, 10-15% reduction in costs utilised to procure the material.• Analysed the company production and sale data, and created the employee timetable sheet on the basis of the worker skillset, manpower and time required for each process, and demand/production scale.• Provided effective and data-driven recommendations to launch new product lines in the organization by utilizing the current resources (current portfolio, land, labour expertise, equipment type and cost, local and export demand etc).

Secured 3rd Position in 2023 Minne Mudac Case Competition• Identified factors that tended to influence home-game attendance for MN Twins, and analyzed the distribution of home-game attendance for all the MLB teams across teams, leagues, geographic regions etc• Deployed boosting machine learning models such as Random Forest and XG Boost to predict the pre-season game attendance for all 2023 MLB teams’ home games, and also built a dynamic prediction model using external data such as All Star player count, cumulative home team win percentage, weather, fan voting data etc that could be used at any time-point in the season to improve upon the predictions made for attendance at home games to be played, say in the following week. • Solely developed a model-driven approach for creating an optimal 2023 home-game schedule for the MN Twins that maximizes the game-by-game attendance. Installed feature engineering and identified the important & popular months, days, and timings that pulled attendance, and set a priority scale on the other MLB teams based on historic attendance data

•Conducted data analytics events such as Tableau, VBA and Text-Mining workshops in collaboration with Hackwagon for 30 students every semester•Organised and administered Tech and Career Management seminars and webinars in collaboration with Tech Tribe to assist students penetrate the IT Industry

I developed correlation and regression analysis to analyse the top 3 sources of micro plastic pollution in Singapore. As such, the team analysed the effects of micro plastic pollution on aquatic and human health, and identified top 5 countries that contribute significantly to micro plastic pollution. Based on the results, the team provided recommendations to the AON health analytics department and government agencies to impose specific policies and interventions to curb down the effect of micro plastic pollution on health

I developed an optimally accounting capacity planning strategy based on market research and insights, UPS customer feedback and historical trends. We conducted a descriptive network analysis to identify over 50 hotspots and active routes based on UPS trade and capacity data. We recommended insights on the basis on the insights and integrators such as DHL and FedEx to improve country-to-country capacity planning.

• Spearheaded a team of 5 to gather customer satisfaction data from 20+ global customer segments entailing 1600+ clients• Explored and analyzed the data obtained using Python, Excel and R programming to prepare a report with actionable insights across 12 touchpoints including customer support, order management and supply fulfillment among others.• Identified top 5 factors influencing the Net Promoter Score (NPS) using machine learning; Provided data-driven recommendations for improvements based on these factors

•Collaborated with data scientists to analyse 2 new fabric products that had a high selling potential in Latin America•Facilitated in studying various market conditions and criteria for trading (importing/exporting) fabrics and yarns•Implemented data-crunching and prepared reports using excel and visualisation tools such as Power BI and Tableau to study trade analysis and competitors’ data