EDW
Finance and crypto
algorithmic trading
SHOW HN2011
How HN took it
2 positive, 2 neutral or asking, 0 mixed, 4 critical, out of 8 comments about the project. Thread score -0.14.
Performance: 0 for, 2 againstDesign: 2 for, 0 againstExecution: 0 for, 1 againstIdea: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Demo web interface looks impressive and is worth a look
From 2 comments
Since this article doesn't mention it clearly, the demo is really nice, and worth a look: http://edwardworthington.com/
copper on HNLooks impressive, particularly if those are real trading results. One concern I immediately have is overfitting, particularly for claims about how various difficult values have…
aothman on HN
Objections
Reported 92% trade success rate suggests in-sample backtesting and overfitting
From 3 comments
Looking at the web interface, it is claiming a 92% success rate on trades. That clearly indicates to me that those results are "in-sample". In other words, the model was trained…
cschmidt on HNYep, it's the same thing as "testing on the training set". With memorization, one can achieve almost 100% on the training set. I'm not saying that EDW is doing this, but I'd be…
ajays on HNLooks impressive, particularly if those are real trading results. One concern I immediately have is overfitting, particularly for claims about how various difficult values have…
aothman on HN
No mention of transaction costs or slippage
From 2 comments
Looking at the web interface, it is claiming a 92% success rate on trades. That clearly indicates to me that those results are "in-sample". In other words, the model was trained…
cschmidt on HNWhen modelling hypothetical trades do you account for slippage and transaction costs?
b0b0b0b on HN
Closed source, so results are hard to verify
From 1 comment
This looks interesting. Even though it's closed-source, the architecture is interesting. As an amateur, I'm always stymied by the lack of data. For intra-day trading, where do…
ajays on HN
Large drawdowns in the P&L sheet
From 1 comment
If you look at his P&L sheet he has some largish drawdowns, with a lot of neutralish trades. I'd prefer to see smaller, but more consistent wins.
spitfire on HN
Requests
Explain the machine learning method and whether test data is separate from training data
From 1 comment
if you use some kind of regularization (e.g., if you think the parameters are sparse) it's possible to fit to such a large space without overfitting. this is common in machine…
dododo on HN
Show risk-oriented portfolio construction and alpha calculation
From 1 comment
I accidentally down voted but meant to up vote. I agree. Also, this appears to have no risk-oriented portfolio construction. You are calculating alphas somewhere, right? (not to…
joshu on HN
Questions
Where does the intraday data come from?
From 2 comments
This looks interesting. Even though it's closed-source, the architecture is interesting. As an amateur, I'm always stymied by the lack of data. For intra-day trading, where do…
ajays on HNThere is data everywhere, and a lot of it is crap. Before you ask yourself what kind of data you need, you must ask yourself what kind of models you want to build. You can buy…
lrm242 on HN
Why year-to-date and month-to-date values do not match, and why liquid equity exceeds account value
From 1 comment
Why don't the values for year-to-date and month-to-date match? Is it a fake mock or a bug? Why is Liquid Equity significantly greater than Account Value? Is it another fake mock…
benmccann on HN
Does the model account for slippage and transaction costs?
From 1 comment
When modelling hypothetical trades do you account for slippage and transaction costs?
b0b0b0b on HN
Alternatives named
Exchange depth-of-book data feeds (NASDAQ ITCH, NYSE ArcaBook)
From 1 comment
There is data everywhere, and a lot of it is crap. Before you ask yourself what kind of data you need, you must ask yourself what kind of models you want to build. You can buy…
lrm242 on HN
Nanex NxCore tick data
From 1 comment
There is data everywhere, and a lot of it is crap. Before you ask yourself what kind of data you need, you must ask yourself what kind of models you want to build. You can buy…
lrm242 on HN
Interactive Brokers market data
From 1 comment
There is data everywhere, and a lot of it is crap. Before you ask yourself what kind of data you need, you must ask yourself what kind of models you want to build. You can buy…
lrm242 on HN