“FIN Status Report 2017-2-20”版本间的差异
来自cslt Wiki
(以“{| class="wikitable" !People !! Last Week !! This Week |- | Yang Wang|| read some papers.<br> found some bugs in our code. || test our strategy<br> 1. impact of...”为内容创建页面) |
Zhangyuxin(讨论 | 贡献) |
||
(3位用户的5个中间修订版本未显示) | |||
第4行: | 第4行: | ||
|- | |- | ||
| Yang Wang|| | | Yang Wang|| | ||
− | + | give a talk about understanding deep learning.<br> | |
− | + | try RMSProp optimizer, weight decay and obtain smooth predicted sequences.<br> | |
+ | try industry stock and obtain highly correlated predicted sequence.<br> | ||
+ | try to add index data and obtain more accurate predicted value. | ||
+ | || | ||
+ | study the stock selecting model.<br> | ||
+ | study the architecture of the network. | ||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
|- | |- | ||
| Yuxin Zhang|| | | Yuxin Zhang|| | ||
− | <br> | + | Try to use DDPG to predict a better limit order price.<br> |
|| | || | ||
− | + | Debugging DDPG and do experiments. | |
|- | |- | ||
|- | |- | ||
| Yaodong Wang|| | | Yaodong Wang|| | ||
− | + | Pick stable stocks and Leading stocks | |
|| | || | ||
− | + | Continue to pick Leading stocks and Make database smoothy to use | |
− | + | ||
|- | |- | ||
| Tongzheng Ren|| | | Tongzheng Ren|| | ||
− | Implement | + | Implement:<br> |
+ | regularization: L2-norm, dropout, batch normalization(including some bugs)<br> | ||
+ | filters: MA, wavelet<br> | ||
+ | Implement index data.<br> | ||
+ | Improve strategy.<br> | ||
|| | || | ||
− | + | Improve strategy. | |
|} | |} |
2017年2月20日 (一) 08:08的最后版本
People | Last Week | This Week |
---|---|---|
Yang Wang |
give a talk about understanding deep learning. |
study the stock selecting model. |
Yuxin Zhang |
Try to use DDPG to predict a better limit order price. |
Debugging DDPG and do experiments. |
Yaodong Wang |
Pick stable stocks and Leading stocks |
Continue to pick Leading stocks and Make database smoothy to use |
Tongzheng Ren |
Implement: |
Improve strategy. |