simra.net

[5/19: fixed the pdf link]
Summary of a Vanguard study:
http://monevator.com/methods-of-making-stock-market-predictions-dont-work/
Link to the study:
https://personal.vanguard.com/pdf/s338.pdf

Note that the methodology is applied only to predicting whole market returns: it isn't applied to choosing individual stocks.

Bitcoin exchange MtGox is unavailable due to DDOS attack. https://m.facebook.com/MtGox/posts/459849287432817 Bitcoin value plunged by 20% on btc-e as a result. This is a crazy volatile horse trading market. My sense is that arbitrage opportunities are not only limited by liquidity but also by daily transaction limits.

Bitcoin is the new speculation hotness. Never mind that it costs more in energy to create a bitcoin than the coin is actually worth.

Various tweaks to the model over the last few days, as well as some backdating and thinking about how to make picks. I'm still working on some formatting/html stuff to make this stuff more browsable but in general you can find the picks after the close each day at, for example, /stocks/topStockPicks-2013-04-03.html, and the latest at /stocks/latestStockPicks. Full backdated index at http://simra.net/stocks.

First trial run of the model based on today's closing prices. Let's see how they look next Friday, shall we?
http://simra.net/stocks/latestStockPicks.html

Rank Ticker
1 CECO
2 GTAT
3 TTI
4 DM
5 CWTR
6 IQNT
7 LAWS
8 COCO
9 MOV
10 NVTL
11 SFY
12 LINC
13 DGII
14 WGO
15 SAH
16 EBIX
17 CBR
18 ENTR
19 STRI
20 AKS

Happy Math.Pi day!
3.

Interesting research paper. Once I've read it completely I'll share some thoughts.
http://www.vatsals.com/Essays/MachineLearningTechniquesforStockPredictio...

UPDATE 3/16: Ok, I read this over and there's not really anything there of interest. As an aside I ran some experiments last week but had to rebuild my system shortly after due to a HD failure. Once I get the data back from my backup I'll share.

Fellow MSFTie John Langford shares his thoughts on stock prediction. http://hunch.net/?p=210

Pasting below some old correspondence with a friend. This was my first cut at applying a machine learning approach to trading.

In general I am skeptical of books about trading strategies. If you have a successful strategy, why would you need to write a book? Hence the literature is more likely than not to be populated with a minefield of failed strategies. All that said, here are some books and articles worth taking a look at. Some I have read, most are on my reading list.