Frank Astier

I wrote a model format converter for another LI system recently and included a model name in the output file. I'll see how to "finish that up" by surfacing the...

Assigning to myself as I am working on normalization right now. @XianXing - can you review this [PR](https://github.com/linkedin/photon-ml/pull/242), and let me know if it is actually incorrect from an algorithm...

Yes, we are having it reviewed by Ankan too. What it does is only setup normalization contexts in GAME and then call the same machinery as photon. If it was...

@XianXing - what is the real impact of not having this? Is it correctness? Is it performance? Is it required to compute variances correctly?

So, it is correctness of _variances_, only. The correctness of coefficient means themselves does not depend on that, right?

This one IMHO would be best handled by the community - meaning that at LinkedIn, we are pretty busy with features needed by LinkedIn. We can chaperone the development of...

@XianXing 179 was merged in Nov 2016. Moreover, we are going to redo the `Driver` so that it is more like a "script" calling library functions to prepare the data,...

The basic design for this should be a `ParquetDataReader` that outputs a `DataFrame` and other data structures needed by `GameEstimator.fit`. We will keep it as `help wanted`: it is good...

We are thinking about it. The issue was brought up recently.

We have a settings file for IDEA at LinkedIn that we might be able to share on github.