Backtesting Opportunity

[smallStops]

Hello All. I am looking to backtest some equity strategies over a very long period of time based on some fundamental and technical data. I am willing to pay someone for their work if they have the ability to do this and also have access to fundamental and price data from S&P compustat database which has quarterly data going back to 1962. As I know this is a very broad description private message me if you have an interest for more information and have the S&P compustat database required.

Excelsior

If your budget is not "stretchable" to infinite.
CQG has a very good database, and you can actually get some of their staff
to do the work for you.

 

[Jerry030]

Excellent points. Only a tiny portion of what worked before up to 2000s worked now. A review of all trading books that had backtesting results will convince any skeptic. Data-mining has destroyed most of edges. My guess is that oif before the 2000s existed X number of edges, now the number id down to 0.001X. This is one of the most important articles I have ever read.

Sergio,


Excellent article that you pointed to in "This is one of the most important articles I have ever read".


It has many right on points particularly that most people do not have the education or skill set to not be trapped by randomness is the design of a trading system. However it makes at least one serious error when taking about "data mining bias". The reason you use knowledge discovery or data mining is to discover what you do not know. If you knew it already you could just code it and would not need to mine huge datasets for undiscovered knowledge. The author almost implies that this process is a doomed enterprise that will be contaminated with curve fitting regardless.


Such is not the case but it requires careful design and rigid segregation of datasets. Take what many would call Evolutionary Computing or Genetic Algorithms. Here billions of attempts will be made to discover a relationship among N elements, factors or measures that deliver a given fitness function (profitability). The trap for most people is using the same data set for both discovery and evaluation. The simple solution is to not let the discovery engine develop fitness functions from the data used to discover the predictive structures. Force it to blindly apply a proposed structure to a fitness test on fully segregated data. You will find you quickly move from disastrous over fitting to the sparse discovery of component relationships that have some predictive value.

 

[Buy1Sell2]

Data-mining has destroyed most of edges.

The only true edge in trading is capital and the prudent use thereof. Learn to be wrong and be ok with it.

 

[Due Diligence]

Hello All. I am looking to backtest some equity strategies over a very long period of time based on some fundamental and technical data. I am willing to pay someone for their work if they have the ability to do this and also have access to fundamental and price data from S&P compustat database which has quarterly data going back to 1962. As I know this is a very broad description private message me if you have an interest for more information and have the S&P compustat database required.

Excelsior

Hi
I've been trawling this site ( and others) to find whether it is possible to access fundamental data - I looked at Compustat but it is clearly not for the individual trader. Were you able to access fundamental data ( that included deleted stocks) for any market?

 

[TradeAsIGo]

By fundamental data do you mean company filings? Those are available from SEC websites.

 

[ironchef]

The only true edge in trading is capital and the prudent use thereof. Learn to be wrong and be ok with it.

This is from Sergio77's link. I wonder if you have any comments:

http://www.priceactionlab.com/Blog/...-brand-for-traders-is-called-risk-management/

This is a quote from the link:

It is amazing how some people write blogs and even books where they scream loud that the secret to success is risk and money management. If that were the secret, big investment houses would not need all those analysts for every sector of the market and for every major name and would just open random positions and have mathematicians manage the risk. However, the practice of winning investment houses for many years provides a clear indication that identifying value opportunities and the proper timing of trades and investments is the primary key to success. Risk management comes after that. It is important but only as a means of maximizing some objective, in most cases that being the net profit, or minimizing net loss in case that the market turns against them. Thus, those who make the naive claims are empirical fools.

Thanks.

 

[ironchef]

New Edge is likely to be found in the application of ideas from strange places like quantum thermodynamics, fluid mechanics and how some species of firefly in the tropics can synchronize their flashing over many miles of riverbank down to the millisecond without the use of Twitter.

Can you help a mom and pop retail trader like me so I can acquire the knowledge of quantum thermodynamics and fluid mechanics to improve my trading skill?

 

[Buy1Sell2]

This is from Sergio77's link. I wonder if you have any comments:

http://www.priceactionlab.com/Blog/...-brand-for-traders-is-called-risk-management/

This is a quote from the link:



Thanks.

Just ask yourself what the reason is that traders blow up and you'll see that the traders who analyze have no edge over other traders unless they exercise PRM. It's the same with investment houses. There is no edge in analysis---everyone does it. ---The edge is in management of risk. This is all that successful trading is about---there is nothing else.

 

[Buy1Sell2]

When traders blow up or fail, they will tell you that they entered correctly, but got married to their position when it went against them and pulled profits too soon when they were right.

 

[Van_der_Voort_4]

@ironchef

Have you asked yourself a question why on this thread and other where you bring the same subject to @Buy1Sell2 not many people enter the conversation??
I mean accept you and other dude from California @BONECRUSHER ,but i tally both of you as one as your questions are nearly of same character.
For example on other thread 10 000 hours to become profitable there are at least 10 participants.

Is PRM only edge in trading?
Is this rare or even extant?

If people are trilled to participate in thread how 10 000 hours of study make or doesn't make them traders and here is silence then you should have an answer right now and i don't mean to imply whether they're bullshitting or not.

if you don't find solution,it will not change anything,asking won't change anything,