Question on Kelly Formula : Positive Expectancy But...

[Question on Kelly Formula : Positive Expectancy But...]

Edit: sunnyjharris just said exactly what i was going to lol

[Question on Kelly Formula : Positive Expectancy But...]

I used Kelly for strategy which trades by single instrument, I see that perfomance became better only on 10%-20%. is it normal?, or it should gives better upgrates for perfomance?

It's not really improving your returns, i.e. your immediate ones, it should be improving them over time, but the idea is the same as controlling and making sure your capital reserve isnt depleted so much that you can't regrow it.

You may want to look at the Safety first criteria. If you are looking for simple management that could be up your alley. It depends on how much money that you are managing.

[Question on Kelly Formula : Positive Expectancy But...]

I can see a few problems with optimal-f from just a quick look at it though. It is guilty of the same problem that problem that the Kelly criterion is, i.e. not looking at the instances around the mean, only at the estimated values. Does the modified version fix this?? Do you have any links describing its calculation?

 

As far as I can tell it is only useful for ball parking and quick, on the spot math.

 

I looked at this for information on calculating the original "optimal" f.

Contango: Optimal f

 

Thank you.

Silentdud

[Harmonic Trading]

Urma, please explain your indicator in more depth. This is not a thread for marketing and I am sure if people are interested they can read exactly the same material on your indicator website.

 

lol that's exactly the same output as an excel momentum model I built once. You make it sound like it's quantum physics. Post the math not the argument, everyone else can test it.

[Question on Kelly Formula : Positive Expectancy But...]

Hello everyone,

 

I am currently reading about the Kelly formula on various website.

I now understand better that money management is a powerful tool to use when trading.

 

However something escapes me:

Assuming one has a trading system tat delivers a positive expectancy BUT there are fewer winning trades than losing trades, how to use the kelly formula??

 

e.g:

 

winning trades : 45%

losing trades : 55%

 

average win: 2,000

average loss: 1,000

 

expectancy is positive with : 0.45 * 2,000 - 0.55 * 1,000 = 350

 

Yet the K% would be negative because there are only 45% winning trades.

 

K% = (0.45 - 0.55) / 2 (where 2 is derived from 2,000 / 1,000)

 

Is there a more "refined/updated" Kelly formula that addresses this issue or this kind of bet should be considered a bad trade and should be avoided ?

 

Thanks!

 

The Kelly formula is only useful if you are taking on a single trade at once. You will not make money if you play a single trade of the same strategy at one time unless you are highly leveraged or you have a substantial cash reserve. Also you will take larger hits to your cash reserve. It's a good lesson for making basic trades, but it is really poor in terms of actual risk management. I know for a fact that Edward Thorpe used to use it, but he was old school and there have been so many innovations since then.

 

For example, if you play 5 games of poker that are within your bankroll instead of one you are diversifying away some of the risk. On the other hand, when you try to do this with stocks there is a correlation of every single security to every single other security and you need to acknowledge this other wise you will loose a lot of money.

 

It's also important to pay attention to skewness in return distributions (not accounted for in the kelly criteria) and Kurtosis (which Long Term Capital Management ignored and caused them to be ruined).

 

Here are two popular books on portfolio management:

 

Managing Investment Portfolios: A Dynamic Process (CFA Institute Investment Series)

 

The CFA institute publications are usually very good but this book includes extra types of portfolio management which you might not need.

 

You may want to look at this one which is cheaper and its highly rated:

The Intelligent Asset Allocator: How to Build Your Portfolio to Maximize Returns and Minimize Risk

 

 

You should realize that a lot of the theory that is in these can actually be applied to modern portfolio theory. I also highly recommend that you look at some of Edward Thorp's papers, although they are highly outdated.

 

[http://edwardothorp.com/id10.html]Edward Thorps publications[/url]

 

 

Hopefully that helps!

 

-Silentdud

[Timing of Inflows and Outflows]

Hello traders,

 

Let me start with saying that I am an accountant, not a trader. I have several questions closely related to daily trading: how to calculate daily rate of return. Here is my situation. I have a list of daily trading-related information. For each day I have 4 numbers in the list: (1) market value of a position at the beginning of the trading day, (2) its market value at the end of the trading day, (3) total daily amount of inflows to this position (purchases), (3) total daily amount of outflows (sales). What I do not know is when the inflows and outflows occurred during the day. The timing is of course very important. As an example, consider a hypothetical position having value of $10 at the beginning of the day and value of $15 at the end of the day. There was a daily inflow of $3, no outflows. The daily profit is $15 - $10 - $3 = $2. If the inflow occurred, for example, at the beginning of the day, the rate of return would be 2/10 = 20%. If it occurred close to the end of the day, the rate of return would be 2/(10+3) = 15.7%. As I said, I have no information about the timing of the cash flows. In the absence of such information, I have to make some simplifying assumptions about the timing of the cash flows to estimate the daily rate of return. Here are my questions.

 

Do you think I would get the best estimate if I assume that all cash flows take place in the middle of the day?

For some days I know for sure when some inflows and outflows have occurred. For example, on a day when a long position was opened, the first transaction was clearly an inflow (purchase). On the day when a long position was closed, the last transaction was an outflow. For short positions it’s vice versa. My questions are: On a day when a long position is open, would it be realistic to assume that the majority of inflows occurred close to the start of trading activity? Similarly, on a day when a long position is closed, would it be realistic to assume that the majority of outflows occurred close to the end of trading activity?

This question is an extension of the previous one. Suppose that the market value of a position was small at the beginning of the day, and I have information that the total daily inflow was big (compared to the starting market value). Would it be realistic to assume that the majority of inflows occurred close to the start of trading activity? And if the market value of a position was small at the end of the day, and I have information that the total daily outflow was big (compared to the ending market value), would it be realistic to assume that the majority of outflows occurred close to the end of trading activity?

 

I am asking about “typical” daily trading scenarios (understanding there are always exceptions and anomalies). I would be most grateful if you could share your practical experience and answer my questions. Thank you in advance!

 

Dear Max,

 

If by market value you mean portfolio value,your rate of return is just:

ROR =(MVend - MVbeg)/MVend

 

However, if by market value, you mean the FMV of the positions open as part of a larger portfolio, you can probably do this:

ROR = [(FMVclose + outflows)-(FMVopen+inflows)]/(FMVopen+inflows) = return for portfolio portion

 

- ideally you would have a different return for each instance or position, which you probably know

- It is not realistic to assume that the majority of inflows occurred at the start of trading activity.

- I was an accountant too.

 

MC

[Mad Hedge-Fund Trader]

I would suggest you go a different way entirely. Do you need a reading list or something? Do you have a degree?

[Capturing Alpha, Pure Play]

For example:

Short Stock, 10,000/stockprice = shares with a market beta of 1.3

therefore take an offsetting long position in SPY to compensate for beta... (10,000*1.3)/SPY Price

 

However, when using a multi factor: beta market = 1.27

beta SML = -.3..... , etc.

 

Short stock 10,0000

Buy long SPY like above, but how to compensate for other betas?... what else to buy/short?

 

Also has anyone played with using GARCH for fama french four factors??? what sort of time period do you use to estimate beta in these???

 

 

I also found this while I was looking around writing this, which may give me some of the size and style options what I can use:

Fama-French Factor Loadings for Popular ETFs » The Calculating Investor

[Capturing Alpha, Pure Play]

most alpha is simply returns above a benchmark.....this is only relevant to those are happy to loose money when the market looses but claim they outperformed.

Most traders would consider themselves uncorrelated absolute return generators without reference to a benchmark and trading only a few instruments and not a portfolio.....

 

I'm not really looking for a debate. I just need a better way to neutralize most irrelevant portions of the returns so that I can specifically capture this abnormality (and nothing else). What is causing the abnormality and where it is from is separate issue. Im working with event driven stuff. I need a better way to neutralize other return factors aside from the movements relevant to other securities.

[End of QE2 - How Are You Going to Trade It?]

Tam's, how do you plan on actually capturing the returns in that chain through Forex and distinguishing it from noise? The effect from the QE2 ending will probably be realized way ahead of time. I don't think you can play it.

 

I think that the FOMC is going to raise I-rates immediately following. What is core inflation at right now? What are the leading indicators for core inflation saying?

[Capturing Alpha, Pure Play]

From what I understand when you have an alpha generating methodology, you can take an offsetting position in the market to neutralize most of the market risk. Has anyone tried offsetting their positions with industry ETF's instead of using SPY? Also, does anyone know of a simple way to eliminate SMB and HML factors from the payoff??? Are there ETF's with this payoff structure???