TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Google Prediction API

355 pointsby pelleabout 15 years ago

17 comments

m0th87about 15 years ago
This is easily the most interesting announcement so far. Machine learning has so many applications, but its use is constrained by the high barriers to entry. Recommendation engines, for example, are huge sales drivers, but few among even the largest ecommerce stores use them. A simple prediction interface that's built on the ML expertise at Google is a win for everyone.
评论 #1362564 未加载
评论 #1362553 未加载
评论 #1362840 未加载
评论 #1363331 未加载
评论 #1363811 未加载
zefhousabout 15 years ago
I'd love to see how well it could predict comment ratings from Hacker News.<p>The following data would be a good start:<p>1. Text of comment<p>2. How many points the comment has<p>3. How many points the article has<p>4. Time article was posted<p>5. Time comment was posted<p>I'd also be interested to see what kind of user bias there is. If you don't provide user names, you could see what kind of rating a comment <i>should</i> have based on its content, and what rating it actually has because certain users are generally loved (pg) or hated (jasonmcalacanis) by the community.
评论 #1363325 未加载
评论 #1363336 未加载
评论 #1362964 未加载
评论 #1363431 未加载
评论 #1362938 未加载
T_S_about 15 years ago
Not enough details available on how it works. Would rather build my own at this point. Plus the way this is billed oversimplifies the whole model design process.<p>Sorry to sound so negative, but I just earned a PhD in Machine Learning. How would you feel if you were replaced by an API? :-(
评论 #1363143 未加载
评论 #1363348 未加载
评论 #1363956 未加载
metaguriabout 15 years ago
I was guessing that google (in their never-ending desire to consume more data) would want to use us as guinea-pigs to improve their algorithms. It's not 100% clear to me, but from the terms of service:<p><i>By submitting, posting, displaying, or transmitting Data on or through the Service, you give Google permission to process your Data for the sole purpose of enabling Google to provide you with the Service in accordance with its privacy policy. You hereby grant Google all licenses to your Data necessary to process the Data and provide you with the Service in accordance with its privacy policy. As a part of the Service and through provided interfaces, Google may allow you to remotely access, view, and download results of the processing of your Data.</i> (via <a href="http://code.google.com/apis/predict/docs/terms.html" rel="nofollow">http://code.google.com/apis/predict/docs/terms.html</a>)<p>I imagine that they might claim the right to use your data anonymously to improve their algorithms, much like they do for your personal data in their other apps. I mean, what better way to refine their supervised learning algorithms than via an endless supply of training sets? But I hate wading through legalese, anyone have any insights?
评论 #1362706 未加载
评论 #1362692 未加载
评论 #1362963 未加载
friscoabout 15 years ago
Need more information. What kind of algorithms are they employing on the backend?
carbocationabout 15 years ago
From the very little information that I see available so far, it appears that Google will first stab at discrete predictions. That is, I don't see probabilistic output yet.<p>Also, from <a href="http://code.google.com/apis/predict/docs/developer-guide.html" rel="nofollow">http://code.google.com/apis/predict/docs/developer-guide.htm...</a>, it is clear that they perform accuracy analysis using the training data. That is, there is no "testing" vs "training" dataset distinction at this point; there is just cross-validation of the training set.
评论 #1362536 未加载
caffeineabout 15 years ago
Darn ... I'm halfway through writing one of these. I guess I just have to make it better..
评论 #1362995 未加载
jbrennanabout 15 years ago
I knew this was coming.
评论 #1362415 未加载
评论 #1362647 未加载
评论 #1362704 未加载
mseebachabout 15 years ago
Are there any (preferably FOSS) libraries that does anything like this?
评论 #1362422 未加载
评论 #1362420 未加载
评论 #1362562 未加载
natfriedmanalmost 15 years ago
This is interesting:<p>"Automatically selects from several available machine learning techniques"<p>So not only does it learn, it's learning which learning techniques work best for different problems.
mikecaneabout 15 years ago
As a non-techie, I don't understand the language example they're using. It seems to me many prediction engines are originally built to try to forecast winning lottery numbers or other such gambling events. Google expects me to believe they did this for language?
评论 #1362681 未加载
评论 #1362715 未加载
abossyabout 15 years ago
Are there any input/output samples?
评论 #1362561 未加载
评论 #1363466 未加载
tszmingabout 15 years ago
Basically what I see is they implemented an open platform for running classification algorithms that gives discrete categories as output. Automatic selection from multiple machine learning methods - maybe just simple cross-validation.
tybrisabout 15 years ago
"Upload your data to Google Storage for Developers, then use the Prediction API to make real-time decisions in your applications."<p>I can understand the necessity of this, but that'll be some serious lock-in.
评论 #1363463 未加载
lsbabout 15 years ago
Would you give every data point of <i>yours</i> over to Google?
评论 #1362674 未加载
评论 #1362456 未加载
joubertabout 15 years ago
Does google use the data you upload for other purposes besides just driving your (private) results via the prediction api?
评论 #1363236 未加载
cb33about 15 years ago
I predict this will be a hit.