2008 Week 9 Picks

RESULT: 4-0 Perfect!

Last week I felt comfortable about most of my NFL picks, especially Carolina and San Francisco (both ATS losers). Except for last week, after I make my picks, I check how popular these picks are. I look at Yahoo's Spread Pick'em League as well as the NFL Consensus Picks at wagerline.com. Doing this for the past 2 years has given me the mental evidence that popular picks do not do well. I do not have the statistical evidence to back this up, but if I do have some time and need to prove it I will.

Last week the two most popular picks were: SF (67%) and CAR (65%), my two favorite picks for week 8, both did not cover. On week 7, Indianapolis (74%) and the NYJ (73%) were the two most popular, neither covered. Although in week 6, both the Eagles (68%) and the Saints (69%) were the heavily favorites and they did cover. As my previous blog on sample size says, we would need many more games to come to any conclusion on this. My hypothesis is that "popular" games are either 50-50 or slightly below 50%. If a game is so popular wouldn't it be more likely to be wrong? I think this for two reasons: 1) Vegas may be guiding bettors one way for more profits and 2) if many are selecting the game then there is no hidden treasure in finding that there is bias on the spread. This is the goal of a good handicapper, and in my case the purpose of using an advanced mathematical model; to find bias in pricing the spread for a game but if everyone is finding it, it is no secret and there is no need for mathematics.

Whatever the case may be, 2 of my 4 picks this week are the most popular ones, the other two are quite unpopular, I'll let you find out (if you care) which is which. I will stick to the model and disregard whether they are popular or not. If consider popularity, I am tramping with the model and we will never see how good it really is. Enough talk, now the NFL Spread Picks of the Week:

Pick 1: VISITING FAVORITES Philadelphia -7
Pick 2: VISITING FAVORITES Atlanta -3

I can't decide between two picks the model detects as opportunities, KC and MIN. The HOME DOGS KC +9 showed some signs of hope last week, but it was against the over-rated Jets. You can expect them to score about 10 points in this game against the #2 defense in the league. Tampa has struggled on the road losing to the Saints, Broncos, and Cowboys and barely beating the Bears. They might struggle again, probably win, but will the offense produce enough on the road?

The Texans face their easiest challenge on the road after losing the first 3 weeks to a very tough schedule. Now they have 3 wins in a row, of which 2 were against the 2 worst teams in the NFL. Minnesota on the other hand find themselves at having a shot at the division, if they can beat someone in it. By securing a win this week, they might have a chance at it. I do not like the fact that they have no passing game. Even with great WR Berrian and Wade, Mr. Frerotte cannot seem to find them so easily. This makes it hard for them to pull away on a game and win decisively.

I should probably not choose either, what do you think? But instead, I am choosing both and once again distributing wealth evenly to protect my portfolio.
Pick 3: HOME UNDERDOGS Kansas City +9
Pick 4: HOME FAVORITES Minnesota -4.5

Pick 5: Monday Night Football (PIT @ WAS) this pick will be posted on the next blog post...

Read more to see the table with the raw outputs for each game's point spread prediction and confidence measure.

Game	Vegas Spread	Prediction	Confidence

NY JETS @ BUFFALO
-5.5
-7.1
57%
HOUSTON @ MINNESOTA
-4.5
-7.5
58%
DALLAS @ NY GIANTS
-9
-6.5
53%
MIAMI @ DENVER
-3.5
-4.5
51%
NEW ENGLAND @ INDIANAPOLIS
-6
-2.1
50%
PITTSBURGH @ WASHINGTON
-2
-4
64%
JACKSONVILLE @ CINCINNATI
8
6.5
47%
DETROIT @ CHICAGO
-13
-17.6
48%
GREEN BAY @ TENNESSEE
-6
-3.5
46%
PHILADELPHIA @ SEATTLE
7
5
39%
TAMPA BAY @ KANSAS CITY
9
14.0
35%
ATLANTA @ OAKLAND
3
5.9
60%
ARIZONA @ ST LOUIS
3
8.1
45%
BALTIMORE @ CLEVELAND
-1.5
-4.1
51%

Afterthoughts from Week 8 - A bigger Sample Size

Three years ago a friend told me that I should use my analytical skills to predict the point spread. So I decided to build 10 different models, test them, and start making predictions using those models that work best.

I experimented with simple offensive and defensive ratios, various linear regression models to predict point spread, a logistic regression (binary outcome) of the probability that a team would beat the spread, and a neural network to predict straight winners. Neither worked so well in predicting ATS winners.

Then I started thinking of a way to combine and categorize these models in search for games in which the spread is a bit "off". After combining the estimates of those models that turned out to be somewhat successful (>52%, the best only predicted 55%), splitting the point spread and the estimations into categories I started to see some good percentages.

Games for which models predicted the home team to beat the spread and the home team was favorite by 3-4 did the best, on average predicting above 65%. Also, heavily favored visiting teams for which the model predicted they would slightly not cover also did well (63%). But what happened on week 8? Didn't I choose those categories for which the games were predicted to be above 60% successful and only got 2 out of 5? Yes, the problem was the sample size.

I have categorized the point spread into 10 categories and the estimation into 8, this totals 80 different possible categories that a game could land on. Although I have 10 years of historical data, some of these categories have less than 10 games, a very small sample size.

This is why when you see stats like "this team is 5-0 ATS at home on Monday night", you should ignore it. 5 games?, that's it? A reasonable sample size would begin at 30, and once you reach 50 or 60 you can feel confident there is a significant trend.

Looking back at past week's point spread picks, I would have done much better had I sticked with bigger sample sizes. I felt into a gambler's trap; I thought there was a trend and went for it when there was not enough evidence to determine there was indeed a trend. I have already written 50 times,'do not pick a game that does not fall into a category with a sample size above 20 and a confidence level greater than 58%'. This is my 3rd year doing this so I guess it is the lessons that a beginning handicapper learns.

I still believe this strategy will pay off. Currently, we are sitting at 59% post week 4, not bad, but I want to be above 60% by the end of the year. You will keep receiving my analysis and picks of the week, at least this year, if I am not above 60% by the end of the year I will close the blog.

Any comments? Good luck.

Monday Night Football Pick Week 8

After obtaining this week's result data, I decided to run the model again to estimate the point spread on the Monday Night Football game. The result was that the prediction model estimated Tennessee to win by 10, making a 6-point difference between the estimate and the spread. I saw this difference in many games this week that would have won had I picked them. So although the confidence is not so high, a measure I still have many doubts on, I am making an extra pick this week.

MNF Pick: Tennessee -4

2008 Week 8 NFL Picks

After sticking to my model's prediction and ignoring what the consensus and others were saying, we had a solid 4-1 last week. The model correctly predicted and probably "knew" that Carolina would be better at home against NO and that New England had not forgotten how to play defense. I regret picking the Colts last week, but only because it was their first week without RB Addai. In any case, I like the way you did not involve emotion in the decision making and I like how the model is picking up trends that people forget about when a team has one or two rough weeks. Again, the objective is then to minimize risk, make solid NFL picks, and in the long run it shall pay off.

Looking at the stock market down today 500 point and the Dow hitting 8500, NFL betting suddenly seems to provide a safe haven for investments.

The NFL Spread Picks of the Week (8) are:

RESULT: 1-4 Better weeks are around the corner


Pick 1: HOME FAVORITE Carolina -4.5

Pick 2: VISITING FAVORITE Washington -7.5


Pick 3: HOME FAVORITE Pittsburgh -3

Pick 4: VISITING FAVORITE San Diego -3

Pick 5: HOME FAVORITE San Francisco -5.5 Hasselbeck is out, pick is in for this week.

As you can see from the table below (Read More), there could be other opportunities although they did not show all the signs I like to see from my stats. Last week, all the 'other good picks' I mentioned were not good at all. So you might want to disregard these or look at them a bit closer. These games include the 3 Home Favorites by a touchdown: Jacksonville, Baltimore, New England, and the visiting underdogs Cincinnati +10. Good Luck!

NFL predictions against the spread and confidence for all games in week 8:

Game	Vegas Spread	Prediction	Confidence
CLEVELAND @ JACKSONVILLE	-7	-7.1	55%
ARIZONA @ CAROLINA	-4.5	-5.9	63%
OAKLAND @ BALTIMORE	-7	-9.1	54%
CINCINNATI @ HOUSTON	-10	-3.6	56%
KANSAS CITY @ NY JETS	-13	-13.5	53%
INDIANAPOLIS @ TENNESSEE	-4	-6.7	53%
TAMPA BAY @ DALLAS	-3.5	-3.5	53%
WASHINGTON @ DETROIT	7.5	13.1	56%
SEATTLE @ SAN FRANCISCO	-5.5	-6.6	56%
SAN DIEGO @ NEW ORLEANS	3	-0.8	43%
NY GIANTS @ PITTSBURGH	-3	-0.2	36%
ST LOUIS @ NEW ENGLAND	-7	-28.7	50%
ATLANTA @ PHILADELPHIA	-9	-11.4	51%
BUFFALO @ MIAMI	1.5	8.9	50%

NFL Point Spread Standings - Up to Week 7

Not surprisingly, Tennessee has been shocking everyone including bettors. After Vince Young left, nobody thought they would be 6-0 and less so 6-0 ATS this year. Has everyone caught up on this? Is the spread going to over react to them now? I do not think so only because they lack star power. I see the spread under-estimating this team throughout the year, including the coming week against the Colts at home.

I just wanted to put this up there. These numbers do not mean much (to me). If anything, I would be cautious of teams that have a very bad and very good record because the market will start adjusting on the other side. It is interesting to see so far which teams have been over-rated: CIN, DAL, MIN, SF, and DEN and which teams have been under-rated: TEN, TB, ARI, ATL, BAL, BUF. Look at my previous post to see how these teams performed against the point spread in previous years and see if you find any significant trends, if you do let me know.

2008 NFL Records vs. Point Spread

Team	W	L	T	PCT
TENNESSEE	6	0	0	100.0%
TAMPA BAY	5	2	0	71.4%
ARIZONA	4	2	0	66.7%
ATLANTA	4	2	0	66.7%
BALTIMORE	4	2	0	66.7%
BUFFALO	4	2	0	66.7%
CAROLINA	4	2	1	66.7%
CHICAGO	4	2	1	66.7%
CLEVELAND	4	2	0	66.7%
NY GIANTS	4	2	0	66.7%
PHILADELPHIA	4	2	0	66.7%
GREEN BAY	4	3	0	57.1%
NEW RLEANS	4	3	0	57.1%
SAN DIEGO	4	3	0	57.1%
WASHINGTON	4	3	0	57.1%
MIAMI	3	3	0	50.0%
NEW ENGLAND	3	3	0	50.0%
NY JETS	3	3	0	50.0%
OAKLAND	3	3	0	50.0%
PITTSBURGH	3	3	0	50.0%
DETROIT	2	4	0	33.3%
HOUSTON	2	4	0	33.3%
INDIANAPOLIS	2	4	0	33.3%
JACKSONVILLE	2	4	0	33.3%
KANSAS ITY	2	4	0	33.3%
SEATTLE	2	4	0	33.3%
ST LOUIS	2	4	0	33.3%
CINCINNATI	2	5	0	28.6%
DALLAS	2	5	0	28.6%
MINNESOTA	2	5	0	28.6%
SAN FRANCISCO	2	5	0	28.6%
DENVER	1	6	0	14.3%

2008 Week 7 NFL Picks

After a disappointing week 6, I am ready to purely stick to the model's prediction. The Giants loss on Monday taught me a big lesson: forget how a team has been performing, judge the spread only, and remember anything can happen. The objective is then to minimize risk, make solid picks, and in the long run it shall pay off.

The NFL Spread Picks of the Week (7) are:

RESULT: 4-1 ALL RIGHT!!!

Pick 1: VISITING FAVORITE Tennessee -8

Pick 2: VISITING FAVORITE Indianapolis -2

Pick 3: VISITING UNDERDOG Seattle +11

Pick 4: HOME FAVORITE New England -3

Pick 5: HOME FAVORITE Carolina -3

I personally like the Colts rise to performance, Kansas City's face-off with the 5-0 Titan's and Seattle's back-up quarterback and high spread against Tampa Bay. I do not like going against the Saints in their current streak nor do I like the Patriots' increasing troubles, but I will stick to predictions and trends and hence pick CAR and NE. As you will see from the table below, other good picks could be: Jets +3 and San Diego 0. Dallas is off the board with Romo's absence.

As requested by various of my readers, below I have attached the raw output table of my model. The prediction and spread are based on the home team meaning if the sign is negative it favors the home team and vice-versa. The percent confidence is a calculation I make in order to determine which games seem like a good betting opportunity.

Game	Vegas Spread	Prediction	Confidence
INDIANAPOLIS @ GREEN BAY	2	2.7	64%
DENVER @ NEW ENGLAND	-3	-13	56%
TENNESSEE @ KANSAS CITY	8	13.1	57%
MINNESOTA @ CHICAGO	-3	-4.5	54%
DALLAS @ ST LOUIS	7	No Romo	No Romo
DETROIT @ HOUSTON	-9	-16.5	50.5%
SAN DIEGO @ BUFFALO	0	4.9	54%
NY JETS @ OAKLAND	3	5	55%
PITTSBURGH @ CINCINNATI	10	5.9	50%
CLEVELAND @ WASHINGTON	-7	-12.3	47%
SAN FRANCISCO @ NY GIANTS	-10.5	-20.8	46%
BALTIMORE @ MIAMI	-3	-3.8	53%
NEW ORLEANS @ CAROLINA	-3	-1.5	42%
SEATTLE @ TAMPA BAY	-11	-14.0	35%

2008 Week 6 NFL Picks

Last week, we found various visiting teams that were under-rated and came out to beat the spread. This week, I am finding a similar story. Usually, Vegas assigns a 3-point advantage to the home team. Sometimes bettors increase this home field advantage just because they are "good at home" without considering as much who are they playing against.

After going 5-1 last week, I feel comfortable with the amount of data we have for this year in order to account for this year's trends. I have been quite busy lately balancing work and a new baby. This means that I will keep my comments to a minimum. Last week I posted no comments on the games and look at how good we did, for superstition's sake, I will do the same this week. I was still able to run my model, analyze results, and give you the free nfl picks of the week.

In regards to the confidence measure I used to post that some of you have asked for, I have to work on it and measure its true validity. As for now, I suggest an even distribution of capital across the picks you decide to use.

Point Spread NFL Picks, Week 6:

RESULT: 2-3 It's ok, we'll get'em next week.

Pick 1: VISITING UNDERDOG Jacksonville +3

Pick 2: VISITING UNDERDOG Oakland +7.5

Pick 3: VISITING UNDERDOG New England +5.5

Pick 4: VISITING FAVORITE Dallas -5

Pick 5: HOME FAVORITE New York Jets -6

I have to admit that I was also tempted to pick Detroit, a home underdog by 13 against Minnesota. In order to keep the record for the computer picks only, I will ignore it, but personally sounds like a good pick.