Work-progress 2017.08

Daily Report

Date	Person	start	leave	hours	plan	status
2017.8.3	Xin Jing	10:00A.M	7P.M	8h	study RNN	look for possible ways to implement our model
2017.7.4	Xin Jing	10:00A.M	6P.M	8h	study RNN	look for possible ways to implement our model
2017.7.7	Xin Jing	10:00A.M	9P.M	11h	implement RNN for our model	implement an RNN with inputs being past returns
2017.7.10	Xin Jing	10:00A.M	7P.M	9h	implement an RNN with inputs being past returns	implementing
2017.7.13	Xin Jing	10:00A.M	7P.M	9h	implement an RNN with inputs being past returns	implementing
2017.7.14	Xin Jing	10:00A.M	7P.M	9h	implement an RNN with inputs being past returns	implementing
2017.7.17	Xin Jing	10:00A.M	7P.M	9h	realized that base line in python does not converge	re-implemented baseline in R
2017.7.18	Xin Jing	10:00A.M	7P.M	9h	realized that base line in python does not converge	re-implemented baseline in R
2017.7.21	Xin Jing	10:00A.M	7P.M	9h	realized that base line in python does not converge	re-implemented baseline in R
2017.7.24	Xin Jing	10:00A.M	7P.M	9h	comparing results from RNN with those from baseline	very close results but results from RNN not stable
2017.7.25	Xin Jing	10:00A.M	7P.M	9h	changing parameters(hidden layer, time steps) and compare results	still, results good but not stable
2017.7.26	Xin Jing	10:00A.M	7P.M	9h	changing features	try features with past changes of return and past basis. still, results good but not stable
2017.7.27	Xin Jing	10:00A.M	7P.M	9h	changing features	try features with absolute values of past returns. still, results good but not stable
2017.7.28	Xin Jing	10:00A.M	7P.M	9h	changing features	try features with past returns and moving variances, still, results good but not stable; try features with nothing but all ones, still, results good but not stable