Welcome to Neural Network Estimator (NNE)

This website provides the code and documentation for the neural net estimator (NNE), a general approach that uses neural nets to estimate structural econometric models.

Please select the type of NNE below.

Full-information NNE

Based on "Estimating and Assessing Identification of Structural Models via Deep Learning." This NNE uses an entire dataset as input, and automatically exploits variation in data. It is useful for not only estimating but also assessing the identification of a structural model.

Open →

Pretrained NNE

Based on "Pre-Training Estimators for Structural Models: Application to Consumer Search." This NNE pretrains a neural net for a given structural model, so users can estimate the structural model at negligible cost — as easy as running a reduced-form regression.

Open →

Original NNE (limited-information)

Based on "Estimating Parameters of Structural Models Using Neural Nets." This NNE uses researcher-specified moments as input to the neural net.

Open →

Contact

To be added …