<div dir="ltr"><span style="font-size:14px">The link to the paper is:</span><div style="font-size:14px"><a href="http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6137254" target="_blank">http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6137254</a></div><div style="font-size:14px"><br></div><div style="font-size:14px">I've tried to use look through the code. If you have any opinions on my proposal, please feel free to contact me. I am willing to contribute to this project. Thanks.</div><div style="font-size:14px"><br></div><div style="font-size:14px">Best,</div><div style="font-size:14px">Zhaoduo</div></div><div class="gmail_extra"><br><div class="gmail_quote">2016-03-14 21:52 GMT+08:00 Ryan Curtin <span dir="ltr"><<a href="mailto:ryan@ratml.org" target="_blank">ryan@ratml.org</a>></span>:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span class="">On Sun, Mar 13, 2016 at 05:38:22PM +0800, Zhaoduo WEN wrote:<br>
> Hi, Ryan,<br>
><br>
> I just knew about GSOC today and I hope it is not late to introduce myself.<br>
><br>
> I am Zhaoduo Wen, a senior student from Beijing University of Posts and<br>
> Telecommunications.I've been working on data mining and machine learning<br>
> problems for a year and had some experience on recommender systems.<br>
><br>
> >From what I know, although collaborative filtering is faster in prediction<br>
> than matrix factorization framework, either itemKNN collaborative filtering<br>
> or userKNN collaborative filtering has some drawbacks. One major<br>
> disadvantage is that they suffer from low accuracy since there is<br>
> essentially no knowledge learned about item characteristics so as to<br>
> produce accurate recommendations. However, linear sparse model performs<br>
> better both in prediction accuracy and running time. I have read related<br>
> papers and I was lucky to listen to the author's presentation.<br>
> Consequently, I prefer to using a sparse linear model as the alternatives<br>
> to neighborhood-based collaborative filtering.<br>
><br>
> I am enthusiastic for contributing to this project as I will be extremely<br>
> excited if I finish this project and someone uses it in future. I once used<br>
> a library for large linear classification (LIBLINEAR), which has a high<br>
> citation times on google scholar. I was impressed by its fast and accurate<br>
> performance. I wish I could write one someday. I believe GSOC would be a<br>
> good beginning.<br>
><br>
> What is your opinion about my proposal? Hope to receive your reply. Thanks.<br>
<br>
</span>Hi Zhaoduo,<br>
<br>
Can you provide a link to the paper that you are proposing to implement?<br>
<br>
Also, it would be a good idea to take a look through the existing CF<br>
code to see how the sparse linear model you are proposing would fit into<br>
the API.<br>
<br>
Thanks,<br>
<br>
Ryan<br>
<span class="HOEnZb"><font color="#888888"><br>
--<br>
Ryan Curtin | "Leave the gun. Take the cannoli."<br>
<a href="mailto:ryan@ratml.org">ryan@ratml.org</a> | - Clemenza<br>
</font></span></blockquote></div><br><br clear="all"><div><br></div>-- <br><div class="gmail_signature"><div dir="ltr"><div><div dir="ltr">Best Regards,</div><div dir="ltr"><br><div>Zhaoduo</div></div></div></div></div>
</div>