RESEARCH BY INDUSTRY
Find published research and synthetic demonstrations, with planned and developing topics clearly separated.
9 published public-data studies4 synthetic demonstrations51 planned or developing topics
1 published study · 2 planned or developing topics
S04 / Advertising and marketing technology
A marketing leader wants to reach people whose behavior changes because of advertising. Test whether treatment-effect targeting outperforms response-probability targeting at the same contact capacity.
Evaluated public-data study
Read the finding and evidence ↗Potential outcomes; doubly robust learning; causal forest
These topics are separate from completed findings. Each status reflects the work actually performed.
S05 / Advertising and marketing technology
A growth team wants to understand how campaign-credit rules change with attribution windows and incomplete journeys. Study whether sequence-aware conversion forecasts improve prediction and whether channel/touch credit is stable enough to inform further experiments.
Planned topic
Discrete-time hazards; sequence learning; attribution sensitivity
Reconstruct eligible user journeys from timestamped impressions and clicks. Compare last-touch and time-decay summaries with a discrete-time conversion-hazard model and a compact sequence model. Apply the same observation and conversion windows across methods; use only available anonymized touch identifiers.
Evaluation: Use chronological cutoffs, a gap for delayed conversions and user-grouped sensitivity checks. Report log loss, calibration, time-to-conversion error where identifiable, and credit-rank stability under window changes, touch deletion and identity fragmentation. Compare to a no-history baseline.
Boundary: Thirty days of observational, anonymized advertising records do not reveal causal channel lift. Do not convert attribution credit into verified incremental ROAS or invent absent spend fields.
S06 / Advertising and marketing technology
An advertising platform must score high-volume traffic within a serving budget. Determine which model delivers the best calibrated click predictions per unit of memory, latency and training cost.
Planned topic
Sparse logistic regression; factorization machines; Pareto analysis
Use a documented chronological subset first, then a larger scale tier. Compare hashed logistic regression, a factorization machine and one nonlinear interaction model. Keep feature transformations identical where possible; handle unseen categories and changing feature frequencies explicitly.
Evaluation: Hold out later daily files. Measure log loss, precision-recall performance, calibration, peak memory, throughput and p50/p95 latency under a fixed hardware and batch-size protocol. Compare sample-size scaling and ablate interaction features; include cold-start and drift slices.
Boundary: Click labels do not measure incremental sales or advertising profit. Report measured benchmark compute costs separately from extrapolated production costs; do not download or train on the full terabyte by default.
The 60-topic program spans 20 industries, with 9 studies published. Synthetic demonstrations are counted separately. Unpublished topics have no public case-study route.
