I did attempt some modifications.

My idea on folding in scores results in the log likelihood of my solution jumping to NaN, as do a lot of the team rankings, and I'm too lazy to try and figure out why.  So I just went with a version of last year's algorithm.  I should really sit down and do an actual rewrite of things, instead of just pushing data through the same set of scripts I've been using.  It is super convenient to do that, as I was able to download the game score data and get the latent ability model ranks out in about fifteen minutes last night.

Here are those rankings:

#2013           2014            2015            2016            2017         group   game     rank      2017            Team
37.500000       37.500000       46.875000       37.500000       43.750000       1       1       1       43.750000       Villanova
NAN             NAN             NAN             NAN             NAN             1       1       16      NAN             MSM/NO
29.687500       29.687500       42.187500       12.500000       25.000000       1       2       8       25.000000       Wisconsin
-20.312500      -20.312500      -17.187500      7.812500        18.750000       1       2       9       18.750000       Virginia Tech
34.375000       34.375000       40.625000       29.687500       18.750000       1       3       5       18.750000       Virginia
-21.875000      -21.875000      6.250000        28.125000       37.500000       1       3       12      37.500000       UNC Wilmington
46.875000       46.875000       -1.562500       7.812500        25.000000       1       4       4       25.000000       Florida
6.250000        4.687500        3.125000        18.750000       31.250000       1       4       13      31.250000       ETSU
21.875000       26.562500       32.812500       31.250000       40.625000       1       5       6       40.625000       SMU
NAN             NAN             NAN             NAN             NAN             1       5       11      NAN             PROV/USC
20.312500       20.312500       23.437500       17.187500       28.125000       1       6       3       28.125000       Baylor

26.562500       26.562500       20.312500       20.312500       35.937500       1       6       14      35.937500       New Mexico St

-9.375000       -9.375000       1.562500        25.000000       18.750000       1       7       7       18.750000       South Carolina

3.125000        3.125000        -9.375000       10.937500       10.937500       1       7       10      10.937500       Marquette

28.125000       28.125000       40.625000       20.312500       29.687500       1       8       2       29.687500       Duke

-14.062500      -14.062500      -14.062500      -20.312500      12.500000       1       8       15      12.500000       Troy

34.375000       34.375000       46.875000       29.687500       48.437500       2       1       1       48.437500       Gonzaga

10.937500       9.375000        20.312500       29.687500       3.125000        2       1       16      3.125000        S Dakota St

-7.812500       -7.812500       -3.125000       12.500000       18.750000       2       2       8       18.750000       Northwestern

-1.562500       -1.562500       10.937500       9.375000        6.250000        2       2       9       6.250000        Vanderbilt

-3.125000       -3.125000       37.500000       15.625000       25.000000       2       3       5       25.000000       Notre Dame

18.750000       18.750000       3.125000        25.000000       26.562500       2       3       12      26.562500       Princeton

1.562500        1.562500        21.875000       28.125000       28.125000       2       4       4       28.125000       West Virginia

3.125000        3.125000        6.250000        6.250000        28.125000       2       4       13      28.125000       Bucknell

3.125000        3.125000        32.812500       26.562500       25.000000       2       5       6       25.000000       Maryland

14.062500       14.062500       12.500000       34.375000       12.500000       2       5       11      12.500000       Xavier

10.937500       12.500000       1.562500        9.375000        26.562500       2       6       3       26.562500       Florida St

14.062500       14.062500       17.187500       10.937500       29.687500       2       6       14      29.687500       FL Gulf Coast

18.750000       17.187500       17.187500       34.375000       37.500000       2       7       7       37.500000       St Mary's CA

28.125000       28.125000       26.562500       23.437500       28.125000       2       7       10      28.125000       VA Commonwealth

40.625000       40.625000       43.750000       26.562500       40.625000       2       8       2       40.625000       Arizona

1.562500        0.000000        -21.875000      3.125000        20.312500       2       8       15      20.312500       North Dakota

23.437500       23.437500       28.125000       40.625000       37.500000       3       1       1       37.500000       Kansas

NAN             NAN             NAN             NAN             NAN             3       1       16      NAN             NCC/UCD

1.562500        1.562500        18.750000       28.125000       15.625000       3       2       8       15.625000       Miami FL

28.125000       28.125000       18.750000       35.937500       7.812500        3       2       9       7.812500        Michigan St

29.687500       29.687500       26.562500       15.625000       20.312500       3       3       5       20.312500       Iowa St

-3.125000       -3.125000       -20.312500      9.375000        34.375000       3       3       12      34.375000       Nevada

-3.125000       -3.125000       14.062500       29.687500       28.125000       3       4       4       28.125000       Purdue

18.750000       17.187500       9.375000        12.500000       37.500000       3       4       13      37.500000       Vermont

29.687500       29.687500       -7.812500       6.250000        25.000000       3       5       6       25.000000       Creighton

-6.250000       -6.250000       20.312500       3.125000        23.437500       3       5       11      23.437500       Rhode Island

21.875000       21.875000       25.000000       34.375000       37.500000       3       6       3       37.500000       Oregon

18.750000       17.187500       26.562500       18.750000       15.625000       3       6       14      15.625000       Iona

26.562500       26.562500       0.000000        15.625000       20.312500       3       7       7       20.312500       Michigan

14.062500       14.062500       7.812500        -12.500000      12.500000       3       7       10      12.500000       Oklahoma St

37.500000       37.500000       25.000000       23.437500       25.000000       3       8       2       25.000000       Louisville

-17.187500      -17.187500      -10.937500      -23.437500      9.375000        3       8       15      9.375000        Jacksonville St

21.875000       21.875000       20.312500       34.375000       31.250000       4       1       1       31.250000       North Carolina

7.812500        7.812500        15.625000       6.250000        18.750000       4       1       16      18.750000       TX Southern

17.187500       15.625000       28.125000       0.000000        25.000000       4       2       8       25.000000       Arkansas

0.000000        0.000000        1.562500        26.562500       15.625000       4       2       9       15.625000       Seton Hall

12.500000       18.750000       4.687500        -23.437500      23.437500       4       3       5       23.437500       Minnesota

NAN             23.437500       3.125000        23.437500       40.625000       4       3       12      40.625000       MTSU

-4.687500       -4.687500       18.750000       17.187500       23.437500       4       4       4       23.437500       Butler

10.937500       10.937500       9.375000        21.875000       31.250000       4       4       13      31.250000       Winthrop

32.812500       32.812500       18.750000       18.750000       37.500000       4       5       6       37.500000       Cincinnati

NAN             NAN             NAN             NAN             NAN             4       5       11      NAN             KSU/WAKE

28.125000       28.125000       10.937500       -3.125000       39.062500       4       6       3       39.062500       UCLA

0.000000        0.000000        17.187500       9.375000        14.062500       4       6       14      14.062500       Kent

20.312500       20.312500       26.562500       28.125000       26.562500       4       7       7       26.562500       Dayton

53.125000       53.125000       37.500000       25.000000       40.625000       4       7       10      40.625000       Wichita St

21.875000       20.312500       53.125000       26.562500       37.500000       4       8       2       37.500000       Kentucky

-18.750000      -18.750000      -6.250000       -18.750000      21.875000       4       8       15      21.875000       N Kentucky

12.500000       12.500000       -3.125000       1.562500        10.937500       5       1       11      10.937500       Kansas St

1.562500        1.562500        -9.375000       -14.062500      9.375000        5       1       11      9.375000        Wake Forest

0.000000        0.000000        0.000000        -7.812500       6.250000        5       2       16      6.250000        Mt St Mary's

-6.250000       -6.250000       -10.937500      -15.625000      14.062500       5       2       16      14.062500       New Orleans

18.750000       18.750000       17.187500       20.312500       12.500000       5       3       11      12.500000       Providence

-15.625000      -15.625000      -12.500000      14.062500       23.437500       5       3       11      23.437500       USC

35.937500       35.937500       26.562500       -9.375000       26.562500       5       4       16      26.562500       NC Central

-20.312500      -20.312500      28.125000       -12.500000      15.625000       5       4       16      15.625000       UC Davis

That probably won't be formatted like garbage.  The NaNs here are for the games that have multiple options, and as such don't have a name in the score data.  I don't think any of those actually matter, as those teams aren't very good, and I don't have them advancing at all.  I'm also pulling in my calculated ranks for the teams from previous years, which I only really used for the ties (which I don't think had to go back further than two years) and also to get a "how good is this team, really" feel.  That's what led me to accept a larger than expected share of "upsets," defined as when the published lower-rank team beats a published higher-rank team.

My bracket is then:

I apparently didn't put in a score.  96-82, using a factor of 2.2 on the rank values to put it in the right range.

Gonzaga is the highest ranked team in my calculations, but I went with Villanova because they've been more consistently good.  I'm not 100% sure of that, but for something I only care enough about to think about like two hours a year, it's good enough.

I actually clicked through to make the "Heart of the Cards" bracket as well, which uses the calculated ranks straight, with no fudging based on the previous years:

106-89, using the same factor as above.

This one has a lot more "upsets", and I intentionally took Wichita State out of my bracket early, because I'm still grumpy about two years ago.

I did download the 538 numbers, but I haven't sat down to turn that into a bracket.  I wonder if Barack Obama is going to release one, since I don't care about the fascist asshole who replaced him.