Archive for September, 2010

When training the ANN, it is worth visually inspecting everything for possible unexpected anomalies. For example, it is worth watching the distribution of the inputs, the outputs, visualizing the weights. When visualizing the strength of the weights, you can spot if a weight is too weak (its input is irrelevant; you can chuck that input; […]

Notice that so far we have used 200 days lookback for estimating the day-of-the-week behavior, so we used a 200 days training set. When we normalize the targets (next day %gain) in the training set, what we basically do is that we subtract the previous 200 days average daily %gain (and we may opt to […]

We achieved about 10-14% CAGR over 5 years. That is quite remarkable, but we are set back by a couple of signs. For example, the flimsy D_stat(%) performance. Usually the directional accuracy we achieved is only about 51.5%. (see previous posts) That is a not a good sign. Let’s see a chart from a backtest […]

Common sense says a group is better than a standalone expert. But what if the expert is very good…? We have made 2 tests for determining the optimal number of epochs. One for a standalone ANN and the other for an ensemble of 20 ANNs. See images here: Click for the bigger image. For the […]

When we eliminated the validation sets from the training samples, we opted to use a fix number of epochs to train. An epoch is one step of the training when all the available training samples are shown to the NN. We have already written about the optimal epoch for standalone ANN. See one of the […]

An intuitive explanation. Look at this chart that shows the average daily %return distribution from 2004 to 2005 for the day of the week. As usual, on the X axis, we show the day of the week. 1 means Monday, 5 represents Friday. Average daily %return distribution from 2004 to 2005. In this 2 years […]

To shed light on the importance of adaptive methods, we show 3 charts here. These show the next day average %returns for different periods. On the X axis, we show the day of the week. 1 means Monday, 5 represents Friday. Overall, Friday’s next day (that is Mondays) %returns are bearish. However, there are 2 […]