shoulda
EWM Redux
Just a few days ago I found some old Neural Market Trends posts that I archived when I switched between blogging platforms. These were mostly about my Stock and Forex trading using AI (aka Machine Learning). While I was more lucky than right w.r.t. to AI in a strong trending market, the posts serves as a good reminder of the longterm investing strategy. I traded the EWM ETF back in April 2007. You can see it was in a nice upward trend and was trading last at $11.80.
Coulda, Woulda, Shoulda - March Machine Learning Mania 2016
The March Madness competitions have the perfect trifecta for regret: repeated leaderboard feedback, ability to tweak probabilities based on personal biases, and a wealth of different data points. So what would you do differently for next year? The only tweak I did was changing the round 1 probabilities for seed 1s to 100% on one submission. I should have gambled a lot more because my two submissions are so similar. I didn't notice this cause I just saw that the predicted champions were different without realizing all the probabilities are within 2-3% of each other.