So basically what I'm saying is that the figures for average error are based on predictions made both during stable time periods and volatile time periods. However, you are still right - it is true that this is much more accurate when the price is less volatile. When the price starts changing a lot, it could have larger errors in predictions. This is mostly the case when real-world events affect the price of bitcoin, since obviously there is no way the software can foresee something like mt gox getting hacked or china changing its policy on bitcoins.
Some real world events that swing prices are foreseeable to some degree. It would be awesome if your bot could scan news articles and find patterns, example: find an article that was posted by atleast 5 different sources with a same or very similar title/keywords. Then the bot would have to determine whether or not the news is good or bad, or the bot could alert you of the news and you'll tell the bot whether or not the news is good or bad.