In the last few years, firms such as Meta, Amazon, LinkedIn, and TikTok’s owner ByteDance have also begun to develop the technology.
Spotify is not the only tech company racing to build machine-learning models that can reason about cause and effect.
In contrast, the Spotify team’s machine-learning model is general purpose and can be used to ask multiple counterfactual questions about many different scenarios. But those researchers built a bespoke statistical model by hand just to ask that one question, says Gilligan-Lee. This replicates the result of the 2020 study, which also used counterfactual reasoning. They found that changing just the detail of where the child drank and maintaining other conditions, such as how the water was treated at home, did not have a significant impact on the outcome, suggesting that the reduced levels of childhood diarrhea were not (directly) caused by installing pipes and concrete containers. Gilligan-Lee and his colleagues ran this scenario through their model, asking whether children who got sick after drinking from an unprotected well in the actual world also got sick after drinking from a protected well in the fictional world. Before installing concrete walls around wells across the country, you need to be sure that the drop in sickness was in fact caused by that intervention and not a side effect of it.
But you need to be sure what caused it, says Gilligan-Lee. In 2020 researchers investigated whether installing pipes and concrete containers to protect springs from bacterial contamination in a region of Kenya would reduce levels of childhood diarrhea. The Spotify team tested their model using several real-world case studies, including one looking at credit approval in Germany, one looking at an international clinical trial for stroke medication, and another looking at the safety of the water supply in Kenya. “It lets you answer any counterfactual question about a scenario that you want,” says Gilligan-Lee.
The result is a general-purpose computer program for doing counterfactual reasoning. Gilligan-Lee and his colleagues used the framework of twin networks as a blueprint for a neural network and then trained it to make predictions about how events would play out in the fictional world. The models are linked in such a way that the model of the actual world constrains the model of the fictional one, keeping it the same in every way except for the facts you want to change. Twin networks treat counterfactuals as a pair of probabilistic models: one representing the actual world, the other representing the fictional one.
0 kommentar(er)
