Method
Causal graph / DAG
Encoding assumptions in a DAG; backdoor criterion and adjustment sets.
11 cases from 9 companies apply Causal graph / DAG. 2 report results in production. Includes variants: Backdoor adjustment.
Typical tasks: Measure impact without an A/B test, Decide who gets an offer, Optimize decisions, Forecast demand and load and 4 more. Companies: Lyft, T-Bank, Sber, Skoltech, Walmart, DoorDash and 3 more. Often combined with: Backdoor adjustment, Double machine learning, Causal inference (general), Uplift modeling, Instrumental variables and 19 more.
How Developer Productivity Changed with AI4SDLC Tools![]() | ![]() | banking | 2026-05 |
| Problems and Prospects of Causal AI | general | 2026-05 | |
Causal Discovery on Real Data: Combining Causal Graphs, Uplift and LLMs![]() | ![]() | banking | 2026-05 |
| AI for Pricing: What to Entrust to an Agent and Where Causal Analysis Is Unavoidable | retail | 2026-05 | |
| Causal concept-based explanations | fintech | 2025-10 | |
| Modern Methods for Estimating Causal Relationships with Big Data | general | 2024-05 | |
| Data Science That Is Useful for Business | general | 2024-05 | |
| Fundamentals of Causal Discovery and Causal Impact Analysis | retail | 2024-03 | |
| Causal Forecasting at Lyft (Part 2) | mobility | 2022-08 | |
| Causal Forecasting at Lyft (Part 1) | mobility | 2022-06 | |
| Using Back-Door Adjustment Causal Analysis to Measure Pre-Post Effects | food-delivery | 2022-06 |

