A service-operations metric layer that keeps arrivals, backlog age, administrative closure, and resolution quality from being treated as the same outcome.

Business questionA service team sees large request queues and wants to move capacity, but complaint count alone cannot show which work is old, which queues are slow, or whether a closed request was actually resolved.

Decision signalThe model treats one NYC 311 request as the source grain, keeps open work at the analysis cutoff, and separates observed lifecycle metrics from outcomes the public source does not contain.

Open case study

Product Analytics

Product analyticscustomer growth

Online Retail: Finding the Customers Behind Repeat Revenue

A transaction analysis showing where repeat revenue comes from and which markets deserve closer growth attention.

Business questionThe retailer had many transactions, but it was not clear which customers and markets created repeat revenue.

Decision signalAfter cleaning 541,909 transactions, the analysis found 4,338 identifiable customers and a strong concentration of revenue among the highest-value customers.

Open case study

Product analyticsgrowth analytics

Marketplace Supply and Demand: What Can the Public Data Tell Us?

A limited-data marketplace diagnosis that separates recorded trips from the requests and driver hours needed to measure imbalance.

Business questionA citywide incentive can be expensive when the real problem is concentrated in a few time and location windows.

Decision signalOfficial TLC data shows when recorded trips and observed driver coverage move, but it cannot directly show all ride requests or unserved customers.

Open case study

Experimentation & Growth

Experimentation & growthgrowth analytics

Campaign Incrementality: Did Advertising Create New Customers?

A randomized advertising analysis that separates additional conversions from customers who would have converted anyway.

Business questionA campaign can increase reported conversions while adding little incremental value if it mainly reaches people who were already likely to act.

Decision signalIn the official Criteo benchmark, the assigned advertising group converted 0.115 percentage points more often than the control group.

Open case study