I have been actively building, analyzing and deploying new models based on the new infrastructure. In order to easily swap models in and out the feature calculation engine is now running on all cylinders - calculating all 650 features - and running a lot slower than before. Some used few, some - like the current one - used a lot of them.
Speaking of the current model; it is based on roughly 60,000 company statements, both quarterly and annual spanning 15 years; from December 31st, 1995 to December 31st, 2010. It makes good use of a couple of hundred features, mainly past relative price patterns and variations on dozens of measures of company strength versus peers.
The expanded date range (compare to previous models built on 5 years) provides the model with data points of various "markets" - bulls, bears, bubbles etc.
I ended all CAPS predictions so as to start fresh with these new models. Will most likely add functionality to the website which does similar tracking so I don't have to spend as much time just entering predictions manually in the Motley Fool CAPS.
Showing posts with label data quality. Show all posts
Showing posts with label data quality. Show all posts
Tuesday, May 3, 2011
Monday, March 21, 2011
A quick look at the worst performing picks
QPSA predicted +0.1786 vs market on 1/28/11. Has since fallen 61% vs market -0.2%. Seems the market changed its mind very rapidly and very aggressively. Clear example of numbers vs sentiment.
MTRX predicted -0.1094 vs market on 2/11/11. Has since increased 16.92% vs market decrease of -1.72%. Others agree - recent rise in crude prices, refiner crack spread etc directly affect this refiner servicer and market changed its mind.
SEED predicted +0.1579 vs market on 2/3/11. Has since fallen -19.05% vs market -0.73. It turns out the prediction is based on 9/30/10 stmts and not the latest 12/31/10 ones. The initial prediction was correct - pending new information which it lacks and it is indeed critical. The latest stmts indicate year-on-year decrease for the same qtr hence the price decline since those stmts were filed/published. In addition, we lack qtrly stmts basing the prediction on just the annual ones which indicate strong growth. Will change the system back to the initial 3 month timeframe - if no stmts within that timeframe then no prediction!
MTRX predicted -0.1094 vs market on 2/11/11. Has since increased 16.92% vs market decrease of -1.72%. Others agree - recent rise in crude prices, refiner crack spread etc directly affect this refiner servicer and market changed its mind.
SEED predicted +0.1579 vs market on 2/3/11. Has since fallen -19.05% vs market -0.73. It turns out the prediction is based on 9/30/10 stmts and not the latest 12/31/10 ones. The initial prediction was correct - pending new information which it lacks and it is indeed critical. The latest stmts indicate year-on-year decrease for the same qtr hence the price decline since those stmts were filed/published. In addition, we lack qtrly stmts basing the prediction on just the annual ones which indicate strong growth. Will change the system back to the initial 3 month timeframe - if no stmts within that timeframe then no prediction!
Subscribe to:
Posts (Atom)