You are hereFinal Submission Countdown
Final Submission Countdown
Contributed by Lester Mackey
Only sixteen minutes remained in the $1 million Netflix Prize competition when I handed over the final set of predictions to the Ensemble team captain. The members of our newly minted team had been working furiously through the night, hoping to improve upon our previous day’s score of .8554. It was hard to believe that just twenty-four hours ago we had passed the four-team coalition that had occupied the first place spot for the last 29 days. There was little time to celebrate; the previous leaders would not go down without a fight, so we had to be ready with something better. A call had been issued for any remaining valid predictors, anything that could tip the scale in this final day, and our members around the globe had answered the call: nearly 200 new predictor sets, some previously passed over for their poor performance and others newly conceived only moments prior, had flooded in from all corners of the team. It was now up to our blenders to work some last-minute magic.
11:26 AM
me: gabor -- here's my new best
i don't know how well it will do
but it's possible it will give .8553
11:27 AM
Gabor: what does the blender say?
me: 0.855345926622 so, cutting it close
Our submission window opened just 9 minutes before the contest closed. Gabor, our captain, had asked me to give him a countdown to our submission time via Google Chat.
11:28 AM
me: 5 minutes
There was nothing left to do but wait.
11:29 AM
me: 4 minutes bpc tied us booo
Indeed, the previous leaders had issued their final submission and risen to tie our score. I decided to check the Ensemble mailing list to gauge our members’ reactions. Some expressed delight, others, alarm. David W. repeatedly expressed confusion about why we hadn’t submitted, as only less than 1 minute remained in the contest. (His clock was 13 minutes fast.)
11:30 AM
me: 3 minutes
11:31 AM
me: 2 minutes
11:32 AM
me: wait peng says he has .8552 !!
That’s right: one minute before our scheduled submission time, I spied a post by Peng revealing his latest blending effort. With an estimated score of 0.85525, it soundly trumped our intended submission. I logged onto the Vandelay Industries server to retrieve the predictions file but didn’t know which of the several hundred files was the right one to download.
11:33 AM
me: Peng -- what file is it quick!
No response. Peng, you see, unbeknownst to me or anyone else had lost his internet connection and had texted the first post by Blackberry.
11:34 AM
me: WHAT FILE IS IT???
Jacob: This is the best RMSE we’ve seen so far, right?
I vote we swing for the fences and submit this one!
Gabor: 1 minute and i have to submit!!!!!
11:35 AM
me: WE DON'[T KNOW WHICH FILE--HURRRRRRRRY
Ces: SHouldn't we submit NOW?
Gabor: Lester!!!!!!!
You can imagine my frustration.
It was now two minutes after our intended submit time and seven minutes until the contest closed. I searched frantically through the folder for files with .85525 in the name but couldn’t seem to find any.
11:36 AM
Gabor: !!!
me: i don;'t know!! i can't find it!
Gabor: ok i submit yours
And then, I saw it.
11:37 AM
me: wait
i found it
opera_est_0.855259.txt.gz
11:38 AM
Gabor: i'm uploading
me: ok, awesome
Gabor: i'm afraid it was late
me: uh oh it's not 11:42 yet
11:39 AM
Gabor: but uploading is slow
me: 4 minutes to spare
it registered
Gabor: ok submission successful :)
Yes, submission successul.
me: That's what this team's all about -- living on the edge :)
congratulations,
reading those final moments felt like the climax of an Action\Thriller movie, :)
Fascinating experience, congratulations to the entire team. I'm curious what happens to the algorithm(s) now though? I'm working on loose pattern matching problem (semantic tags extracted from social media) in an attempt to help focus real time internet conversations topically, as well as provide advertisers with a chance at relevancy to te individual.
Any chance your team is interested in reapplying the methodology to other spaces?
Team Ensemble,
1) Everything Everything Everything ... for a reason
2) If you're not living on the edge ... you're taking up too much space
3) Quitting IS Never An Option
Please do not spend too much time figuring out (although ... figuring things out ... seems to be your business model) what the world of granola is doing intersecting with your world.
I heard about the Netflix contest and somehow, link after link, found myself reading your countdown page.
Exhilarating ... to read about your last minute dash.
I understood ... and that prompted my acknowledgment.
Whatever the outcome ... having no regrets is as good a win as any ... although the cash would be nice too :-)/
Dr. GRANOLA®
occasionally masquerading as ...
Saul Wilner
Founder & President
1-800-GRANOLA, Inc
drgranola@800granola.com
确实是很激动和惊险的最后一刻。可惜当时我在睡觉。
It is a really exciting moment, but I am sleeping at that time.
Wow, I actually felt anxiety reading this!
I've had some really hard-deadlines, couriers picking up optical media (?), secure ports opening for new code shipments and upgrades at 3am etc... so I know that sometimes, at the last minute, you see something and you think... until next time? now? rebuild? can we? should we? OMG!
Snapping a final release build DVD of a huge banking system that was (ceremonially... i know... wtf) going to be delivered was funny... something had fucked up... or taking an encrypted build system on site... then downloading new code over a 20mbit connection and running an on the fly build because 'the wrong version of a spec file was used the whole of the last month' and shit like that... aaah good times....
I was told by a very good teacher of mine, the times he was editing 'by eye' assembly code during life tests of a system that would cost thousands if it failed during this test... I love programming on the edge :-)