# 6th Place Solution Summary

6th place solution is a neural network consisting of 3 components:
Meta Encoder  - taking as input meta features hostgal photoz, hostgal photoz err, is galactic and summary stats for flux and flux_err as min/max/mean etc.
Light Curve Encoder - bidirectional GRU taking as input grouped by day flux, flux_err, detected and time difference
Spectroscopic Redshift Predictor – two fully-connected layers for predicting hostgal specz
Outputs of these 3 components are fed into two last fully-connected layers for predicting class probabilities.
Light curve encoder was pre-trained as autoencoder on test data.  Spectroscopic redshift predictor was also pre-trained on test data objects for which hostgal specz is available.
Augmentations. Three types of augmentations are performed:
flux as a Gaussian with standard deviation flux_err
hostgal photoz as a Gaussian with standard deviation hostgal photoz err
randomly dropping observations
Top submission is an average of 5 cross-validation runs of 3 neural network variations.