2008 NFL Week 17 Picks

In order to keep this experiment running, I will post this week's computer generated picks. This week may be one of the hardest weeks for prediction since there is much more volatility than usual caused by coaches sitting down their key players. Will Eli Manning play the whole game? Will the wide receivers from Arizona play their hardest? True, these player's salary depends on statistics they accumulate the whole year, but risking an injury will cost them more than having a couple more catches.

For us making point spread predictions, we'll stay away from games whose team have already clinched the playoffs. This week, there are two games that really stood out to me as I thought the point spread was a bit off. The statistical model also confirmed this and made me like these two picks even more, these are: Chicago @ Houston and Denver @ San Diego. San Diego favorite by 8? This is going to be a close game my friends. Chicago playing for a playoff hope should not be an underdog. So those are my first two picks. The rest to follow:

Pick 1: Visiting Underdog Denver +8
Pick 2: Visiting Underdog Chicago +3
Pick 3: Visiting Underdog Miami +2.5
Pick 4: Home Favorite Baltimore -12.5
Pick 5: Visiting Underdog Washington +3 PUSH

Game	Vegas Line	Estimate	Prediction-Vegas

ST LOUIS @ ATLANTA
-14

clinch

clinch
SEATTLE @ ARIZONA
-7
clinch
clinch
OAKLAND @ TAMPA BAY
-13
-18.0
-5.0
DETROIT @ GREEN BAY
-11

-15.4
-4.4
DALLAS @ PHILADELPHIA
-1
-4.7
-3.7
KANSAS CITY @ CINCINNATI
-2.5
-5.5
-3.0
NEW ENGLAND @ BUFFALO
6
4.4
-1.6
JACKSONVILLE @ BALTIMORE
-12.5
-16.2
-3.7
CAROLINA @ NEW ORLEANS
2.5
2.2
-0.3
CLEVELAND @ PITTSBURGH
-11
clinch
clinch
MIAMI @ NY JETS
-2.5
1.5
4.0
DENVER @ SAN DIEGO
-8
-3.6
4.4
TENNESSEE @ INDIANAPOLIS
3
clinch
clinch
WASHINGTON @ SAN FRANCISCO
-3
5.8
8.8
CHICAGO @ HOUSTON
-3
7.3
10.3
NY GIANTS @ MINNESOTA
-7
clinch
clinch

Afterthoughts Week 16

This model does not work. I have to go back to the drawing board and come up with a better way to predict sides against the point spread. I give a lot of credit to the people at Vegas putting the point spread, they know how to make the outcome almost random. I have always thought and still believe that there are games out there that are not well aligned, that the point spread is off. It is easy to see those games after the fact, but not right before the game starts. I do also think that 3 or 4 picks a week is a lot, if a system were to find these opportunities, they would be less than two games a week, if that.

What am I going to do now? I do not know. Hopefully I will have a good run in the playoffs (like I did last year) and push up the percentage to at least 55. In the off-season is back to crunching the numbers and searching for data and different methodologies to test. If by back-testing a strategy I get above 57% say, then I will introduce it next year. If I find a couple of strategies, then I might post picks from all 3 strategies and we shall all witness the best one. Still, I have a lot of work to do. For now, I will finish this season with the same methodology I described before.

2008 NFL Week 16 Picks

Regardless of how awkward the picks might seem, last week showed me there is no sure pick. Who would have thought that Cincinnati could beat Washington? How many think Jacksonville can beat the Colts? Or Seattle beating the Jets? It can happen. When you look closely at the Colts scores, a lot of their games have been close. Yes, they have 7 in a row which makes it a scary bet.

I will not try to make the case for each pick this week. In this exciting NFL week, it will be strictly the model making the picks. We'll stick to the theory I proposed in my previous blog because I do believe this model is of good value. The theory was to pick the games with the highest difference between the point spread prediction and the Vegas spread. Games with teams that have clinched playoff spots are out. The question is how many games; this week lets pick those games with difference of 5 points or more (except for the Tampa Bay pick). Without further ado, here are week 16 NFL picks of the week:

NO Pick 1: HOMEDOG Seattle +5 injury
Pick 2: HOMEDOG Jacksonville +6
Pick 3: Visiting Favorite San Francisco -5.5
Pick 4: Visiting Favorite Houston -7
Pick 5: Home Favorite Tampa Bay -3.5

Good luck!

As always, if you read more you will find the point spread predictions for each game of the week. Notice I have remove the confidence measure, it was about time.

Game	Vegas Line	Estimate	Prediction-Vegas
NY JETS @ SEATTLE	+5.5	injury	NA
INDIANAPOLIS @ JACKSONVILLE	6	0.9	-5.1
MIAMI @ KANSAS CITY	4	-1.0	-5.0
BUFFALO @ DENVER	-7	-11.7	-4.7
SAN DIEGO @ TAMPA BAY	-3.5	-8.0	-4.5
CAROLINA @ NY GIANTS	-3	-7.2	-4.2
CINCINNATI @ CLEVELAND	-3	-6.7	-3.7
GREEN BAY @ CHICAGO	-4	-6.7	-2.7
PITTSBURGH @ TENNESSEE	2	-0.7	-2.7
BALTIMORE @ DALLAS	-4	-2.0	2.0
PHILADELPHIA @ WASHINGTON	5	7.2	2.2
ATLANTA @ MINNESOTA	-3.5	-1.0	2.5
NEW ORLEANS @ DETROIT	7	11.4	4.4
HOUSTON @ OAKLAND	7	13.0	6.0
SAN FRANCISCO @ ST LOUIS	5.5	12.9	7.4
ARIZONA @ NEW ENGLAND	-8	2.3	clinch

Afterthoughts NFL Week 15 - Point Spread Predictions

Another bad week for picks not so bad for point spread predictions. Let me explain. When I first started making building a model that could predict point spreads I, I wanted it to be as precise as possible given team-level data. That is, using team records, game results, home field advantage, and offensive/defensive stats I build a bunch of models in order to pick the most accurate. That was step 1.

The next step was to determine which of these predictions was best to use in making picks. The obvious candidate was those predictions that were most different from the point spread. This theory was thrown out because predictions were way off when there were key injuries or teams had clinched playoff spots at the end of the season.

I knew it would be a waste of time to try to pick every game. So the goal was to find a way to use the predictions to make picks. That is when I built the now useless confidence levels you will not see posted on the blog again. These confidence levels were merely the percentage of times predictions picked correctly against the spread in the past 7 years given the point spread and the difference between the point spread and the prediction.

I have noticed the past 3 weeks that the original idea works well if one manually disregards games with key injuries (something I cannot do automatically given the data I have). Lets take a look at this past week point spread predictions posted on the previous blog. These are the 6 games with the biggest difference in point spread vs the Vegas spread. Disregarding the Giants/Dallas game due to injuries to Burress and Jacobs all picks won except the Washington/Cincinnati game and Seattle/St. Louis was a push. Unfortunately, it is hard for me to go back to historical data and test this theory, but until I have a better confidence measure, this is what I will use to make picks from now on. Last year, I made a huge comeback in the playoffs, only making one incorrect pick. There's still hope.

Game	Vegas Line	Estimate	Difference
PITTSBURGH @ BALTIMORE	-2	2.9	4.9
WASHINGTON @ CINCINNATI	7	12.6	5.6
SAN FRANCISCO @ MIAMI	-6.5	2.9	8.4
NY GIANTS @ DALLAS	-3	5.7	injury
SEATTLE @ ST LOUIS	3	8.6	5.6
BUFFALO @ NY JETS	-9	-4.3	4.7
NEW ENGLAND @ OAKLAND	7	11.3	4.3

2008 NFL Week 15 Picks

Last week the picks did not go well and I do not have much explanation other than bad luck. Any betting system will have streaks of good and bad luck, the important thing is to stay calm in both states. Keep your pick and betting strategy constant. For amount allocation stay with Kelly's formula and bet proportional to your bankroll. Not only will your chances of ruin are almost zero, but also when the winning streaks come, your winnings will increase exponentially.

As of this week, some teams have already clinched their spot on the playoffs. My stats cannot account for benching star players and for players not giving their 100%. That is, my model assumes that each player and coach will play with the same intensity and desire to win as throughout the year. For that reason, we will stay away from such games.

This week, the model predicted 4 visiting team favorites. For these games it might be that the home-field advantage is over estimated. Some of these games have also over shadowed teams that have been performing not so well recently, but still have a decent team. For example, Green Bay @ Jacksonville. Green Bay, although a very unstable team right now which I thought deeply to stay away from, has demonstrated a this year a few times that it can play. Rogers is good, well at least when facing bad defenses. The Jaguars on the other hand have probably thrown the towel. The market has devalued the Packers almost to the Jaguars level, buy low, Green Bay.

Kansas City has definitely improved but they are still a struggling team. Although the Chargers beat them by a point at home, they are coming off a strong win. Their mere hopes of playoffs is still alive and will pick up their play Sunday, hopefully.not enough to get swept off by the Chargers. Sell high, buy Chargers.

The next two picks are hitting on other two really struggling teams. Not the Lions, their spread of 17 might be too high, but picking the Lions is a risky move. I am talking about the Bengals and Raiders. They are both going down, by a lot. Well there they are this weeks "computer made" NFL picks. Noticed all 4 picks are VISITING FAVORITES, not my style, but that is just they way it is this week.

Pick 1: VISITING FAVORITE Washington -7
Pick 2: VISITING FAVORITE Green Bay -2
Pick 3: VISITING FAVORITE New England -7
Pick 4: VISITING FAVORITE San Diego -5.5

And below, the table with point spread predictions and confidence levels:

Game	Vegas Line	Estimate	Confidence
TAMPA BAY @ ATLANTA	-3	-2.4	57%
TENNESSEE @ HOUSTON		NA	NA
PITTSBURGH @ BALTIMORE	-2	2.9	56%
WASHINGTON @ CINCINNATI	7	12.6	61%
NEW ORLEANS @ CHICAGO	-3	-4.6	53%
SAN FRANCISCO @ MIAMI	-6.5	2.9	53%
MINNESOTA @ ARIZONA	-3	-3.5	53%
NY GIANTS @ DALLAS	-3	5.7	50%
CLEVELAND @ PHILADELPHIA	-14	-18.0	48%
SAN DIEGO @ KANSAS CITY	5.5	7.0	48%
DENVER @ CAROLINA	-7.5	-5.8	46%
SEATTLE @ ST LOUIS	3	8.6	44%
DETROIT @ INDIANAPOLIS	-17	-13.9	44%
BUFFALO @ NY JETS	-9	-4.3	43%
NEW ENGLAND @ OAKLAND	7	11.3	58%
GREEN BAY @ JACKSONVILLE	2	4.7	56%

2008 NFL Week 14 Picks

NFL picks is very much like marketing, half science and half art. You use statistics to uncover opportunities and patterns out of all the overwhelming amount of information. With this information in hand, you use 'art' or experience you have had with the numbers to make wise decisions.

Injuries in major positions bias my point spread predictions. It is better to stay away from volatile teams with recent roster changes in RB, QB, or LB positions. This is why this week, although I personally like Tennessee to roll over Cleveland, and the model also predicts they will do so, we stay away and wait for calm water. Of the other 3 NFL games with double-digit spreads I talked about in my previous post, I will stay away from all of them. Although I think St. Louis might be a good bet with Steven Jackson back in the lineup, my model cannot pick up his presence well and predicts Arizona will barely cover. Enough about what my model does not pick. Here are the opportunities it found and that I as an experienced handicapper, agree with its pick.

RESULT: 1-3 No Good

Week 14 NFL pick-les of the week:
Pick 1: VISITING FAVORITES Jets -4
Jets lose one game and suddenly their spread drops to 4 points? They were favorites to the Rams on the road by 9 and at home with Denver by 8. This team is thinking Super Bowl and San Francisco is thinking next year. Favre, pass it to your teammates and you shall cover.

Pick 3: HOME FAVORITES Da Bears -6
Wake up and smell the coffee Orton. You have a decent defense, an awesome running back, and a great wide receiver/punt returner. If you have to go to your old ways of handing off the ball all game, do it!

Pick 4: VISITING UNDERDOGS Atlanta +3
They beat them once and they'll beat them again. Brees, they have you all figured out.

Pick 5: HOME FAVORITES Green Bay -6
So the Texans beat the Jaguars, Browns, Bengals, and Lions, big deal. Packers have had a tougher schedule and have crushed the Bears, Colts, and Seahawks.

I forgot to post the week's prediction table. I will do so this week if you read more. Good luck!

Game	Vegas Line	Estimate	Confidence

NY JETS @ SAN FRANCISCO
4
7.1
59%
MINNESOTA @ DETROIT
7.5
14.5
57%
JACKSONVILLE @ CHICAGO
-6.5
-9.5
56%
ATLANTA @ NEW ORLEANS
-3
0.3
56%
CINCINNATI @ INDIANAPOLIS
-14
-8.1
54%
DALLAS @ PITTSBURGH
-3
3.5
52%
TAMPA BAY @ CAROLINA
-3
2.9
52%
WASHINGTON @ BALTIMORE
-5.5
-4.8
51%
KANSAS CITY @ DENVER
-10
-16.1
50%
OAKLAND @ SAN DIEGO
-10
-13.5
50%
NEW ENGLAND @ SEATTLE
5
8.0
49%
PHILADELPHIA @ NY GIANTS
-7.5
-5.7
49%
HOUSTON @ GREEN BAY
-6
-11.7
49%
ST LOUIS @ ARIZONA
-14
-15.1
NA
CLEVELAND @ TENNESSEE
-14
NA
NA
MIAMI @ BUFFALO
-1
-3.1
37%

Big Spreads in Week 14

Last week, 12 visiting teams covered the point spread on NFL games. The two biggest spreads were covered this week. At the beginning of the season, spreads over 10 were covered about 20% of the time, but in the past two weeks this number changed to just under 60. Underdog teams included in these big spreads have been Detroit, St. Louis, Cincinnati, and Seattle.

This week there are four games with big spreads in favor of the home team. Will the visiting teams cover these spreads? Or will the heavily favorites run by these unfavorable teams?

As of today, four games have double-digit spreads. First, Cincinnati at Indianapolis. The Colts have won their last five games, but none above 7 points. Cincinnati is partly throwing the towel already and the Colts might use this game to blow them out and lift their spirits for the playoffs.

Also receiving double-digits point spread for Week 14 is Cleveland at Tennessee. Las week, Derek Anderson injured himself bringing in the backup's backup for week 14. Ken Dorsey is in, who? One might think that Tennessee should easily cover, but Cleveland this year being so unpredictable, no one knows how this new comer can come out throwing.

The Oakland @ San Diego game opened at 10, and today is was at 9.5. San Diego has lost the last 3 games by less than 6 points. At 4-8, the Chargers do not look that well off than Oakland. The Raiders have had surprising wins against Denver in week 12 and the Jets in week 7. The have kept Carolina and Miami within 9 points in the past 3 weeks. Was this spread estimated based only on their previous game this year when Oakland lost by 10? I'm leaning Oakland, but we'll see what the predictions say.

Finishing off the double-digit spreads on the Week 14 Bodog's NFL point spread is St. Louis at Arizona. The Rams have lost their last six games, four of which were blowouts. Last week, they kept it close with Miami, why? I think Steven Jackson's presence in this team is huge. I think they will give the Cards a hard time (if Jackson plays) this week.

Afterthoughts Week 13

Why were the picks so good this week? Was it because in this odd week visiting teams covered the spread in 12 of 16 games and all my picks were for visiting teams? Was it because the model is earning back some of its losses from that past two weeks to jump back to 60% levels? Or was it because my picks did not involve games whose teams did not have serious roster changes? I do not know the answer to these questions, but I do know that we went 4-0 and we are back above 60% ATS!

After two weeks of disappointing results, the predictions really stepped up to the plate this week. Now I am confident again that there is something in this complex statistical model. Many stopped visiting the site because of these two disappointing weeks, but some encouraged me to keep going forward.

Like many statistical models, this one predicts well in the long-run, but is volatile week by week. That is why I encouraged, in a previous blog, to use betting size wisely. In the stock market, it is hard to predict exactly when stocks will hit bottom, but with fundamental analysis, one can spot stocks that will pay back well in the long run. Not all stock picks will pay off, but one makes sure that those that do, do well. My picks and model behave the same, not every week is going to be a winning week, but in the long run and with careful handling of the money, the payoff will be profitable. I cannot be those handicappers that advertise every week that they went 4-0 or 3-1 last week. Nobody can do that, they have to be lying! I can only say that I have been at 60% in my first two years of giving free handicapping picks.

Looking forward to week 14.

Jaime