Trends Are Not Your Friend

[danrubin12]

Hi all - recently wrote this article on trends. Would love feedback. DM if you have any questions or want a copy of the underlying binomial calculations.

~~~~~~~~~~~

We’ve all seen it before.

“Since 2005, underdogs of more than six points have gone 162-138 (54%) against the spread in the first round of conference tournaments.” – some crappy “analyst”.

I get it. Trends are easy to comprehend and fit a narrative to. Media companies and sportsbooks (which are becoming increasingly intertwined) love them because they can be queried very quickly, and they give the illusion that you have an edge.

But that’s exactly what trends are. An illusion. If you look hard enough anywhere, you can manipulate any data set to craft a narrative about a trend that doesn’t actually exist.

Most trends are a result of variance. And as a result, you can find a trend for just about anything. Thankfully, we have the tools to assess variance which can help explain why trends can be 1) so prevalent yet 2) so meaningless at the same time.

Binomial Distribution
A binomial distribution is a discrete probability distribution of the number of successes in n-numbered trials. Binomial distributions help us answer questions such as “what’s the probability of getting 7 or more ‘heads’ if I flip a coin 10 times?” (17.2% for those wondering). Using binomial distributions, we could answer the question: “If a monkey picked the ATS winner in 300 games, what’s the probability of Mr. Monkey wins at least 162 games (54%)?”

Answer: 9.2%

Back to Trends

So how do we apply this to trends? Can you say – if you pull a random 300-game sample, there is a 9.2% probability of finding a trend that wins a 54% clip? Not quite.You see 9.2% represents a single tail of the distribution of outcomes as displayed below.



When someone is seeking a trend, they aren’t discriminating on which side of the tail that they identify as a trend. While we’ve correctly identified that there is a 9.2% probability that Mr. Monkey could win 162 or more games (out of 300), there is also a 9.2% probability that Mr. Monkey loses 162 or more games (out of 300). Therefore, there is an 18.4% chance that Mr. Monkey’s win probability is either 1) ≥ 54% or 2) ≤ 46% (in which case someone might say it is a ‘trend’ to fade Mr. Monkey).



Thus, if someone takes a random 300-game sample, we know that there is an 18.4% chance that they will find a ‘trend’ with a winning % of 54% or greater.

Finding a Trend

If you pull a 300-game sample size and don’t find a trend, are you going to stop looking, or try again? Try again, of course. So how long will it take you to find a trend?

Not very long.

Since there is an 18.4% chance that you will find a trend, we also know that there is an 81.6% chance that you don’t find a trend on your first try. So you try a different ‘system’ (I hate that word). How many tries does it take (on average) for you to find a trend? We solve for smallest value of n (number of tries) that satisfies the following formula:


Solving for n, we determine that if you try 4 different potential ‘trends’ you will likely (>50%) find one. Due to the long tail nature of the distribution, on average it will take you 5.4 (1 / 18.4%) tries to find a trend with 54% win probability over a 300 game sample size.

Average Number of Queries to Find Various Trends

Below we’ve computed the average queries required to find various trends. For example, If you're looking for a trend that wins in 18 out of 30 games (60%) it will only take you 2.8 queries, on average.


So What’s the Big Takeaway?

The big takeaway is that most trends that are thrown out by ‘analysts’ are completely meaningless since many trends can be found with just a little bit of querying of various game samples. Even trends that are “statistically significant” can be found. This does not mean that they are necessarily predictive.

Trends are more than likely the result of data mining and have little predictive value. When evaluating supposed trends, ask yourself, is there something fundamentally driving this anomaly, or is this simply just noise?

[Roscoe_Word]

Gettin on em early, and bailing when they wane, separates the men from the boys.

I haven't quite figured out how to do that yet.

[asiagambler]

You ignored the most important aspect of trends

It's not how often the trend wins but by how much that's important and gives actual predictive value

[SBR_Guest_Pro]

i hate the new trend of the mom jeans and mom jean shorts that girls are wearing,where the waist comes up super high. That tend needs to end now and go back to daisy dukes

[danrubin12]

Certainly assessing margin of victory is a more granular reflection of past performance, but I wouldn't mistake it for predictive value.

Consider Team A that is 8-2 ATS in it's last 10 games. Covering the spread by an average of 10 points reflects a better past performance (relative to market expectations) compared to an average margin of victory of 2 points. But this still doesn't tell us much about whether the market is correctly pricing Team A in Game 11.

[JohnGalt2341]

Gettin on em early, and bailing when they wane, separates the men from the boys.

I haven't quite figured out how to do that yet.

There's a reason for this, it's because many, if not most trends are merely illusions that probably happened by chance. Don't believe me? ...flip a coin 100 times and record your results on a piece of paper. This is less games than a Baseball season and barely more than an NHL or NBA season.... but will you see trends? Of course you will. Trends are easy to spot out AFTER they happen. But do they mean anything? In the coin flip they mean nothing at all. In sports they may or may not mean something. And I think in many cases they mean about as much as your coin flips. But people like to put meanings behind trends even when they likely mean nothing at all.

Now... imagine instead of having just 1 coin... you have 30 coins and you flipped all of them 100 times. Will you see lots of trends? You certainly will. Do they mean anything? Absolutely not. Getting in on a trend early is nearly impossible for anyone to do consistently. You might get lucky every now and then... but in the long run your trend is likely just a black swan. And for most people... when they spot a trend correctly they say "I CALLED IT!!!" and when they get them wrong... they ignore their prediction completely.

[RudyRuetigger]

There's a reason for this, it's because many, if not most trends are merely illusions that probably happened by chance. Don't believe me? ...flip a coin 100 times and record your results on a piece of paper. This is less games than a Baseball season and barely more than an NHL or NBA season.... but will you see trends? Of course you will. Trends are easy to spot out AFTER they happen. But do they mean anything? In the coin flip they mean nothing at all. In sports they may or may not mean something. And I think in many cases they mean about as much as your coin flips. But people like to put meanings behind trends even when they likely mean nothing at all.

Now... imagine instead of having just 1 coin... you have 30 coins and you flipped all of them 100 times. Will you see lots of trends? You certainly will. Do they mean anything? Absolutely not. Getting in on a trend early is nearly impossible for anyone to do consistently. You might get lucky every now and then... but in the long run your trend is likely just a black swan. And for most people... when they spot a trend correctly they say "I CALLED IT!!!" and when they get them wrong... they ignore their prediction completely.

stupidly wrong in every category

you have to believe in God if you believe a coin flip is random

[JohnGalt2341]

stupidly wrong in every category

you have to believe in God if you believe a coin flip is random

I noticed a "trend" in virtually all of your posts. You strongly disagree with someone, then call them a dumbass or something similar... but you virtually NEVER attempt to explain why they are incorrect and you are correct. You just make your insulting post, and then claim victory and then move on to another thread and do the same thing again.

Let's take a look at some of your recent posts below to various different people:

a few areas had positive results, including china

quit being a dumbass

widely touted?

he said maybe it will work, maybe it wont

stop being a little bitch

go jump from a plane without a parachute you dumb fukkin joke

bro obama did that

quit being a little fukkin fruit loop

Can anyone see a trend here? I certainly can. And unlike most trends in sports... this one is actually REAL. Day in, day out... you will see the same garbage coming from him over and over again. This is the self proclaimed Players Advocate right here.... he never has an answer for anything but he disagrees with everyone that doesn't have Trump's dikk in their mouth. And just like Trump... he always claims to be the victim even when the evidence is obvious.

[jjgold]

Trends are ok to look at but a losing proposition as far as gambling

[RudyRuetigger]

I noticed a "trend" in virtually all of your posts. You strongly disagree with someone, then call them a dumbass or something similar... but you virtually NEVER attempt to explain why they are incorrect and you are correct. You just make your insulting post, and then claim victory and then move on to another thread and do the same thing again.

Let's take a look at some of your recent posts below to various different people:





Can anyone see a trend here? I certainly can. And unlike most trends in sports... this one is actually REAL. Day in, day out... you will see the same garbage coming from him over and over again. This is the self proclaimed Players Advocate right here.... he never has an answer for anything but he disagrees with everyone that doesn't have Trump's dikk in their mouth. And just like Trump... he always claims to be the victim even when the evidence is obvious.

I thought you were a fair independent?

sad to see you come to this

focus on my comment : you have to believe in god if you believe a coin flip is random

[JohnGalt2341]

I thought you were a fair independent?

sad to see you come to this

focus on my comment : you have to believe in god if you believe a coin flip is random

Please explain to me how a fair coin is not random. If it's not random... it should be at least somewhat predictable. Explain to me how so.

"sad to see you come to this" This is another one of your stock comments. Do you know what gaslighting means? Look it up if you don't know. You're one of the top 3 gasligthers on SBR.

[RudyRuetigger]

Please explain to me how a fair coin is not random. If it's not random... it should be at least somewhat predictable. Explain to me how so.

"sad to see you come to this" This is another one of your stock comments. Do you know what gaslighting means? Look it up if you don't know. You're one of the top 3 gasligthers on SBR.

if there is no free will

then everything can be predicted

so when you flip a coin, given the speed, wind, air pressure, when it will be caught, or hit the ground, all of that bullshit


you should know how the coin will land

a coin flip should not be random

[JohnGalt2341]

if there is no free will

then everything can be predicted

so when you flip a coin, given the speed, wind, air pressure, when it will be caught, or hit the ground, all of that bullshit


you should know how the coin will land

a coin flip should not be random

Whether or not there is Free Will is debatable.

I'll go with your argument though... if we are living in a simulation perhaps your theory is correct. However, you would think that someone would have gotten very good at this... at least being able to get 55% correct over a very large sample size. That's only 1 extra correct on average over a sample size of 20. If coin flips aren't random... there should be LOTS of people that can do this. I've never heard of anyone being able to do this anywhere. If someone could do this... you would think someone would have set a Word Record for it. "Most correctly predicted coin flips in 1000 flips" Or something of that nature. I've never heard of such thing... and it's unlikely that anyone can do it. Unless you are omniscient... I don't see any reason to believe that coin flips aren't random. And I've never known anyone to be omniscient.

[RudyRuetigger]

Whether or not there is Free Will is debatable.

I'll go with your argument though... if we are living in a simulation perhaps your theory is correct. However, you would think that someone would have gotten very good at this... at least being able to get 55% correct over a very large sample size. That's only 1 extra correct on average over a sample size of 20. If coin flips aren't random... there should be LOTS of people that can do this. I've never heard of anyone being able to do this anywhere. If someone could do this... you would think someone would have set a Word Record for it. "Most correctly predicted coin flips in 1000 flips" Or something of that nature. I've never heard of such thing... and it's unlikely that anyone can do it. Unless you are omniscient... I don't see any reason to believe that coin flips aren't random. And I've never known anyone to be omniscient.

i stopped reading here

if we get to the point where we know everything, a coin flip isnt random


nothing is random

that has nothing to do with living in a simulation

[RudyRuetigger]

i stopped reading here

if we get to the point where we know everything, a coin flip isnt random


nothing is random

that has nothing to do with living in a simulation

unless you think we can only have exact predictions in a simulation

hasnt that already been proven then?

[JohnGalt2341]

i stopped reading here

if we get to the point where we know everything, a coin flip isnt random


nothing is random

Of course you did. You're intellectually lazy just like most Trump supporters are. Just read and "learn" about what you already agree with and nothing else. Anything you don't already agree with is WRONG!

Make a bunch of unresearched claims all day long every day without doing 1 shred of research on it... and anyone that doesn't agree with you is either a "dumbass" "bitch" or "fruit loop" or any of the other various names that you are projecting upon people.

When was the last time you learned something new that you didn't already know? You should try it sometime. Maybe someday you'll be able work your way up to reading a book.

I take it that you think it is impossible that we could be living in a simulation? Is this true?

[RudyRuetigger]

Of course you did. You're intellectually lazy just like most Trump supporters are. Just read and "learn" about what you already agree with and nothing else. Anything you don't already agree with is WRONG!

Make a bunch of unresearched claims all day long every day without doing 1 shred of research on it... and anyone that doesn't agree with you is either a "dumbass" "bitch" or "fruit loop" or any of the other various names that you are projecting upon people.

When was the last time you learned something new that you didn't already know? You should try it sometime. Maybe someday you'll be able work your way up to reading a book.

I take it that you think it is impossible that we could be living in a simulation? Is this true?

you didnt answer my question

you can turn the tables on your middle school students galt boy, but not me

given that you know every single thing leading up to a flip, the flip should not be random

quit arguing

[JohnGalt2341]

you didnt answer my question
you can turn the tables on your middle school students galt boy, but not me

given that you know every single thing leading up to a flip, the flip should not be random

quit arguing

What was your question?

If coin flips are not random... how come there is not one single person in the world that can predict them?

[asiagambler]

Certainly assessing margin of victory is a more granular reflection of past performance, but I wouldn't mistake it for predictive value.

Consider Team A that is 8-2 ATS in it's last 10 games. Covering the spread by an average of 10 points reflects a better past performance (relative to market expectations) compared to an average margin of victory of 2 points. But this still doesn't tell us much about whether the market is correctly pricing Team A in Game 11.

And why not? It sure tells you a hell of a lot more than if a team was winning by an average of 2 points

Your argument isn't really based on anything. Of course no one knows with absolute certainty how the market is pricing Game #11. That goes for literally anything

But if the market is completely misreading a situation to the point where the margin of victory is way off from the closing line, then it's far more likely something that's been missed and unaccounted for. If this misread turns into a trend, well then it's pretty hard to argue that there isn't an inefficiency there somewhere

[danrubin12]

My argument is that trends are 1) numerous 2) largely reflective of prior performance 3) not necessarily predictive of future performance.

Predictive sports modeling involves coming up with a prediction of a game and comparing it to the market's line. If you are following a trend and not incorporating the market line into your wagering decision you will have no idea if/when the market corrects an inefficiency.

I think you will be hard pressed to find someone who knows what they're doing who blindly follows trends to consistently profit. If this is your strategy, so be it. Best of luck. Simply providing a different perspective here.

[The General]

99% lose...That's a trend I'd bank on..

[jjgold]

General post of year

[asiagambler]

My argument is that trends are 1) numerous 2) largely reflective of prior performance 3) not necessarily predictive of future performance.

Predictive sports modeling involves coming up with a prediction of a game and comparing it to the market's line. If you are following a trend and not incorporating the market line into your wagering decision you will have no idea if/when the market corrects an inefficiency.

I think you will be hard pressed to find someone who knows what they're doing who blindly follows trends to consistently profit. If this is your strategy, so be it. Best of luck. Simply providing a different perspective here.

Who said anything about blindly following trends

That's pretty much THE EXACT OPPOSITE of what I said

"Predictive sports modeling involves coming up with a prediction of a game and comparing it to the market's line"

Way to make a circular argument. I can come up with a braindead model looking at a team's points scored over the last 10 games and just taking the average. Is that going to beat the market? Absolutely not unless the market is composed of cavemen who can't do simple math

You would be surprised just how sophisticated some trends can get. The only thing that matters is the market