Hassam AsgharData & Business AnalystKitchener–Waterloo
I turn messy operating data into decisions.
SQL, Power BI, Python and optimization. Completing a Master of Management Analytics at Queen’s (Dec 2026), and co-running a home-textiles brand where I own every number.
Open to roles in the GTA & Southwestern Ontario · hassam.asghar.work@gmail.com
- ~$1Ma month in billing through data I owned
- −40%financial reconciliation time, with Power BI
- +37%what menu variety adds to hospital food cost
- #1on DrivenData’s Pump It Up leaderboard at submission (team, 0.8308)
Smith School of Business
Queen’s University · MMA
Cowlar Design Studio
Studio of YC-backed Cowlar
Modisoft Inc.
200+ US retail accounts
Hopefield Home
Co-founder
Selected work
Four projects, strongest first.
Each one starts from a business question and ends with what changed. Every number traces to the case study.
Schematic of the pipeline, not measured data — the billing figures belong to a former employer. marks the QA gate I built.
Analytics & BI Cowlar Design Studio, product studio of YC-backed Cowlar
Cut billing reconciliation time 40% on a ~$1M/month billing system
−40%financial reconciliation time, after Power BI replaced manual spreadsheet consolidation
SQL datasets, a QA/UAT gate and Power BI behind a studio’s live fractional-billing pipeline.
Read the case study 5 min read
Accuracy on 3 pump classes — team stacked ensemble, #1 on the leaderboard at submission
Predictive Modelling DrivenData Pump It Up · MMA 869 Machine Learning & AI
Ranked #1 on DrivenData predicting which Tanzanian water pumps fail
#1on DrivenData’s Pump It Up leaderboard at submission; top 3 of 8,657 ranked entries today (team, 0.8308)
Three-class pump-failure model on 59,400 survey records, built around CatBoost’s native handling of 19,000-value location columns.
Read the case study 6 min read
Pieces stranded per colour: packing the minimum combos first strands 42; the LP plan strands 0
Optimization Hopefield Home, the home-textiles brand I co-founded
Packed 6,000 loose towels into 1,000 sets with zero left over
0 of 6,000pieces stranded, against 42 when each colour’s minimum is packed first
An integer program in Excel Solver that turns a towel order into sellable sets without stranding a single piece.
Read the case study 5 min read
3-day food cost per profile — cost-only, 3-day rotation, 2-day rotation
Optimization MMA 861 · Smith School of Business, Queen’s University
Priced hospital menu variety at +37% food cost with a MILP
+37%food cost of menu variety vs the cheapest compliant menu ($6.81 → $9.34 per patient, 3 days)
A mixed-integer menu planner for five clinical diets that puts a dollar figure on menu variety.
Read the case study 8 min read
More work
Coursework, a competition and the tools I’ve built.
Predictive Modelling Team of 5
Predicted auto claims at 0.887 ROC-AUC with plain logistic regression
0.887ROC-AUC on 2,000 held-out policies, vs 0.881 for the best tree model and 0.50 for chance
Predictive Modelling Solo
Chose a turbine model on cost, not accuracy, saving $137,500 a year
$137,500a year saved by choosing the turbine model on cost, not recall (course case)
Predictive Modelling Team of 7 · team lead
Showed the transfer market pays forwards a 76% premium over defenders
+76%market value of forwards over defenders after age and minutes (95% CI +61% to +92%)
Predictive Modelling Self-directed
Reached the top 20% on Kaggle House Prices through better encoding
Top 20%of the Kaggle House Prices leaderboard (score, field size and date not recorded)
Agentic AI Solo
Measured my browser agent over 119 sessions, then rebuilt it
68%of 119 logged sessions weren’t forms, so the form-centred learning loop was retired
Agentic AI Solo build, ~175-person studio
Automated HR letters and the worklogs behind ~$1M/month billing
3HR workflows on one agent: letters, onboarding checklists, and worklogs that fed billing
Experience
Where I’ve done the work.
Nov 2025 – present
Co-Founder & Operator · Hopefield Home
Home-textiles brand on Amazon FBA and Shopify. I own the demand plan, the inventory optimization, the listing analytics and the automation stack behind it.
May 2024 – Jun 2025
Billing & Compliance Analyst · Cowlar Design Studio
Owned the 15+ SQL datasets and Power BI reporting behind a live fractional-billing system processing close to $1M a month. Cut financial reconciliation time 40%.
Jan 2023 – Apr 2024
Customer Support Lead · Modisoft Inc.
Led a team of 7 across 200+ US retail accounts, ran QA on POS and financial datasets, and traced a recurring scan-data discrepancy to its root cause.
Education
Master of Management Analytics
Smith School of Business, Queen’s University
Jan – Dec 2026 · In progress
Bachelor of Business Administration (BBA)
National Defense University
Jan 2019 – Jan 2024 · Islamabad, Pakistan
Toolkit
What I use, grouped by what it’s for.
Analysis & Modelling
- Python
- pandas
- scikit-learn
- CatBoost
- LightGBM
- XGBoost
- statsmodels
- PuLP / Solver
- SQL
- R
Decision Science
- Linear & mixed-integer programming
- Ensembles & stacking
- Clustering (K-Means, DBSCAN)
- Association rules
- Cost-sensitive model evaluation
- Regression & regularization
- Hypothesis testing / ANOVA
- A/B testing
- Forecasting
- Simulation
Communication
- Power BI
- Tableau
- Looker Studio
- Advanced Excel
- Executive decks
- Data storytelling
Engineering & AI
- Claude & OpenAI APIs
- Agentic workflows
- Node.js
- REST / GraphQL APIs
- Google Apps Script
- n8n
- Git
The short version
I came into analytics through operations: three years of support and billing work where I kept hitting the same wall. The data existed, but nobody had built anything that wouldact on it. So I started building. A fractional-billing system that processed close to $1M a month. An HR agent that writes its own documents. A browser agent that fills in forms by itself.
Now I’m finishing a Master of Management Analytics at Queen’s, which gave me the formal half (optimization, inference, machine learning) to go with the engineering half. In between I co-founded Hopefield Home, a home-textiles brand, mostly because I wanted a business where I owned every number and couldn’t hide behind someone else’s dashboard.