# 4 Idiots' Solution & LIBFFM

Dear all,
We have prepared our
[code](https://github.com/guestwalk/kaggle-avazu)
and
[document](http://www.csie.ntu.edu.tw/~r01922136/slides/kaggle-avazu.pdf)
.
In this competition and
[Criteo's CTR competition](https://www.kaggle.com/c/criteo-display-ad-challenge)
, we find field-aware factorization machine (FFM) is a powerful model. We hope this model can be more widely used, so we also release an implementation
[LIBFFM](http://www.csie.ntu.edu.tw/~r01922136/libffm/)
. We are very interested to see if it is effective in other kinds of datasets.
Your questions or comments are welcome! :)
-- 4 Idiots