Counterfactual Forecasting of Human Behavior using Generative AI and Causal Graphs
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908641538342912 |
|---|---|
| author | Uddandarao, Dharmateja Priyadarshi Vadlamani, Ravi Kiran |
| author_facet | Uddandarao, Dharmateja Priyadarshi Vadlamani, Ravi Kiran |
| contents | This study presents a novel framework for counterfactual user behavior forecasting that combines structural causal models with transformer-based generative artificial intelligence. To model fictitious situations, the method creates causal graphs that map the connections between user interactions, adoption metrics, and product features. The framework generates realistic behavioral trajectories under counterfactual conditions by using generative models that are conditioned on causal variables. Tested on datasets from web interactions, mobile applications, and e-commerce, the methodology outperforms conventional forecasting and uplift modeling techniques. Product teams can effectively simulate and assess possible interventions prior to deployment thanks to the framework improved interpretability through causal path visualization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_07484 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Counterfactual Forecasting of Human Behavior using Generative AI and Causal Graphs Uddandarao, Dharmateja Priyadarshi Vadlamani, Ravi Kiran Machine Learning Computational Engineering, Finance, and Science Methodology This study presents a novel framework for counterfactual user behavior forecasting that combines structural causal models with transformer-based generative artificial intelligence. To model fictitious situations, the method creates causal graphs that map the connections between user interactions, adoption metrics, and product features. The framework generates realistic behavioral trajectories under counterfactual conditions by using generative models that are conditioned on causal variables. Tested on datasets from web interactions, mobile applications, and e-commerce, the methodology outperforms conventional forecasting and uplift modeling techniques. Product teams can effectively simulate and assess possible interventions prior to deployment thanks to the framework improved interpretability through causal path visualization. |
| title | Counterfactual Forecasting of Human Behavior using Generative AI and Causal Graphs |
| topic | Machine Learning Computational Engineering, Finance, and Science Methodology |
| url | https://arxiv.org/abs/2511.07484 |