Kelly feels huge

**roasthawg** · 09-27-10, 10:13 AM

I use a flat 2%... still seems big to me, especially after a good win streak. It definitely takes discipline.

**That Foreign Guy** · 09-27-10, 10:32 AM

I use full Kelly but divide my roll in to several parts depending on which system they are so I am sort of only using 5th Kelly overall.

I may well change this once I am very confident in win rates etc.

**CatPulp** · 09-27-10, 11:07 AM

Kelly is contingent on your edge. How big of an edge do you think you have and keep in mind, this has to be statistically consistent, not just a one-off based on the odds offered on one sporting event.

**bztips** · 09-27-10, 11:31 AM

One of Thorp's papers has a good discussion of the tradeoffs in deciding whether/how to use fractional Kelly:

http://www.pitt.edu/~sorc/trade/files/RiskManagement/kelly.pdf

**statictheory** · 09-27-10, 12:21 PM

Not to promote dr bob, but he has some great articles on betting and money management at dr bob sports.

**CatPulp** · 09-27-10, 12:22 PM

Oh, and by the way, if you aren't hitting your bets at at least a 64% success rate, then this bet has a negative expectation value and you should not bet it.

**u21c3f6** · 09-27-10, 01:15 PM

Originally posted by luegofuego

... but doesn't using half or quarter Kelly kinda defeat the whole purpose of a mathemetically optimized bet sizing strategy? ...

Below is an answer I wrote for a past thread on Kelly:

Here is how I look at it and this is also based on many years of use.

Kelly is without a doubt the mathematically proven optimal wager for bankroll growth assuming (and this can be a big assumption) that you know the actual edge of your wager. Early on I used full-Kelly. However, being relatively conservative, I did not like the volatilty that my bankroll had using full-Kelly. In researching money management further, it seemed to me that half-Kelly might be the way to go. The comparison goes like this:

Using full-Kelly, there is a 1/3 chance that your bankroll would fall in half before it doubled. Using half-Kelly, you still have 75% of the growth rate as full-Kelly but with half-Kelly there is only a 1/9 chance that your bankroll will fall in half before it doubles.

Having used both, I am personally much more comfortable using half-Kelly. I prefer to watch my bankroll increase in size by a nice small zig-zag pattern than the more extreme ups and downs of full-Kelly. Once you double your bankroll, you will be making wagers equivalent to full-Kelly of your original bankroll only now with a greater degree of safety.

One other thing I also do is to segregate different types of wagers as well as different odds to determine my edge. For myself, I find that different types of wagers and different odds have a different edge which is critical for the Kelly calculation. If I was to lump all of this into one data pool I could come up with one composite edge but that is not as optimal as knowing that I have a higher or lower edge based on the type of wager and the odds and then sizing my wagers accordingly.

Joe.

**byronbb** · 09-27-10, 07:50 PM

A 2% edge demands 6% at -300 and less than 1% at +300. Flat betting these is a)underbetting and b) over betting, and therefore at least sub-optimal to BR growth. (I am not a math guy but flat-betting might actually increase variance).

It all comes down to how sharp the lines of the sport you are betting are. If it is a huge market like the NFL or the EPL and you can get edges then bomb away full-kelly. With smaller markets use some sort of fraction.

**Flying Dutchman** · 09-27-10, 08:41 PM

There are many historical threads written on Kelly here at the Tank. I'd suggest some research.

**Maverick22** · 09-28-10, 07:21 AM

I dont know about Kelly. But the ladies say Maverick feels huge. Giggidy.

**statictheory** · 09-28-10, 12:43 PM

Originally posted by CatPulp

Oh, and by the way, if you aren't hitting your bets at at least a 64% success rate, then this bet has a negative expectation value and you should not bet it.

yes but his articles are very good

**jgilmartin** · 09-28-10, 02:25 PM

Originally posted by Maverick22

I dont know about Kelly. But the ladies say Maverick feels huge. Giggidy.

Haha I knew it was only a matter of time before someone posted a 'that's what she said' type comment based on the thread title.

**CrimsonQueen** · 09-28-10, 03:09 PM

It's quite a tough decision... but the easy truth is, if you can determine your edge to a T, then you would be stupid not to use Kelly! If you can't estimate your edge to a T (and I'd say this goes for 99% of bettors), then you'd be stupid to use Kelly!

So the question isn't "should I use kelly"...the question is "can I estimate my edge accurately?"

**roasthawg** · 09-28-10, 03:15 PM

Originally posted by CrimsonQueen

It's quite a tough decision... but the easy truth is, if you can determine your edge to a T, then you would be stupid not to use Kelly! If you can't estimate your edge to a T (and I'd say this goes for 99% of bettors), then you'd be stupid to use Kelly!

So the question isn't "should I use kelly"...the question is "can I estimate my edge accurately?"

Good post... estimating the edge is the toughest part by a longshot.