# 3 Idiots' Solution & LIBFFM

Dear all,
We have prepared our codes and documents.
For the codes, please see
[here](https://github.com/guestwalk/kaggle-2014-criteo)
; and for the documents, please see
[here](http://www.csie.ntu.edu.tw/~r01922136/kaggle-2014-criteo.pdf)
.
In this competition and
[Avazu's CTR competition](https://www.kaggle.com/c/avazu-ctr-prediction)
, we find field-aware factorization machines (FFM) are powerful models. We have implemented it in the package
[LIBFFM](http://www.csie.ntu.edu.tw/~r01922136/libffm/)
.
Your comments are very welcome. Thanks!
-- 3 Idiots