TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Better bus predictions (a lot better)

74 点作者 kylebarron超过 6 年前

10 条评论

ajuc超过 6 年前
In my city there is a system like this (all buses have gps, you can look where they are at any time <a href="http:&#x2F;&#x2F;www.sip.ztm.lublin.eu&#x2F;Default.aspx?lang=EN" rel="nofollow">http:&#x2F;&#x2F;www.sip.ztm.lublin.eu&#x2F;Default.aspx?lang=EN</a> ), and on bus stops there are these dynamic timetables <a href="http:&#x2F;&#x2F;rpw.ztm.lublin.eu&#x2F;typo3temp&#x2F;_processed_&#x2F;csm_01_01_594179becd.jpg" rel="nofollow">http:&#x2F;&#x2F;rpw.ztm.lublin.eu&#x2F;typo3temp&#x2F;_processed_&#x2F;csm_01_01_594...</a><p>It&#x27;s working pretty well, the key thing is the point 4 in the article - the timetables show &quot;in X min&quot; if they know how long it will take for the bus to get here, or just &quot;at XX:XX&quot; if they don&#x27;t know for some reason (transmitter or bus broke, whatever) so they just show the scheduled arrival.<p>So you can be pretty sure that if it says it&#x27;s coming in 4 minutes you won&#x27;t be waiting 30 minutes.<p>Clearly marking how sure you are of your prediction is IMHO more important than making very good predictions. I don&#x27;t care if I have to wait 3 minutes or 6 minutes, I do care if I skip another bus waiting for a more convenient one in 3 minutes that never arrives.
评论 #18184986 未加载
kuanbutts超过 6 年前
This is awesome! I fully believe that government procurement needs serious reform, which this article and effort is clearly attempting to address. So, props to David Block-Schachter (the CTO).<p>There are far too many large, bloated consultancies that specialize not in delivering quality products and services, but rather in &quot;surviving&quot; the government procurement process.<p>Props as well to the Swiftly team - I had a change to take a peak at some of the APIs they expose to their customers and it&#x27;s quite valuable. In particular, they roll up stop-pair segment performance on routes by time of day, which allows someone to query for bus performance by discrete route-schedule-segments.<p>Gathering this type of data is quite labor intensive and a significant technical lift (I was once part of a project doing this with GTFS-RT data from the NYC MTA). This type of information, and the broader ecosystem of performance related API services they provide to their users (based off the limited amount I have seen), can enable operators to extract highly articulated performance statistics about their fleet, on their own.
edejong超过 6 年前
Having developed similar systems in the past, I would like to advice against arbitrary boundaries on accuracy.<p>We used a couple of metrics to assess the quality of the predictions. The first one is sMAPE (Scaled Mean Absolute Precision Error), which tells us quickly where and how our predictions fail. We plot this with the precision on the y-axis and the minutes till arrival on x. Also plotted is bias, which is important, especially since you want to be slightly biased towards being too early. Similar axes.<p>Other metrics we used are MAE (Mean Absolute Error), RSE (Root Square Error) and 2D kernel density plots.<p>In the end, for a contract, I would take into account the density of use of these predictions. It&#x27;s nice that you can predict perfectly during the middle of the night, but if that line is not used, it is next to useless. So something like sMAPE * passengers or sth like that.<p>Also, even though I cannot relay this one-to-one to the passengers, a confidence interval on predictions is gold.
evmar超过 6 年前
In case anyone else was wondering, it appears that MBTA here refers to a Boston transit agency.
评论 #18183501 未加载
tzs超过 6 年前
I just skimmed the article, so apologies if this was covered.<p>The article suggests people will use these predictions to spend more time at home before leaving their bus stop. If that is the case, what happens if the prediction says their bus will be, say, 10 minutes later, but then that bus catches some lucky breaks with lights, heavy traffic unexpectedly clears up, etc., and the bus makes up 5 minutes of that?<p>People who relied on the prediction could miss their bus.<p>Is there a mechanism to address this?<p>The only one that I can think of offhand that would cover almost all cases would be if the predicted arrival times are also sent to the buses, and if the buses arrive ahead of the prediction they wait until the predicted time before leaving.<p>You wouldn&#x27;t want to do that for all predictions, though. Maybe only predictions made within 10 minutes of the original scheduled arrival time are binding, or maybe only predictions made when the bus is within three stops of the stop in questions, or something like that.
评论 #18185003 未加载
评论 #18182430 未加载
bsder超过 6 年前
Tell me where the bus <i>IS</i>, dammit. Why is this rolling out <i>after</i> prediction instead of <i>before</i>?<p>Why are we &quot;predicting&quot; at all?<p>Why doesn&#x27;t every bus have a tracker that tells you exactly where it is <i>at all times</i>?<p>This is 2018. GPS with refinement isn&#x27;t rocket science anymore.<p>Tell me where the bus is and I&#x27;ll do my own prediction thanks.
评论 #18181834 未加载
评论 #18181373 未加载
评论 #18181338 未加载
评论 #18190527 未加载
评论 #18183213 未加载
romed超过 6 年前
Awesome. I hope SFMTA can learn from this. They are taking proposals to replace Nextbus currently [1]. When I last measured Nextbus reliability, the first prediction for a bus was weakly correlated with arrival, and the second and third predictions were totally free of information. One of the main problems around here seems to be buses with the route and destination sign set to the wrong thing (e.g. the bus says it is headed to downtown, it&#x27;s actually going the other way) which apparently throws a huge wrench in Nextbus.<p>1: <a href="https:&#x2F;&#x2F;www.sfchronicle.com&#x2F;bayarea&#x2F;article&#x2F;Muni-looks-to-replace-aging-NextBus-system-with-13204933.php" rel="nofollow">https:&#x2F;&#x2F;www.sfchronicle.com&#x2F;bayarea&#x2F;article&#x2F;Muni-looks-to-re...</a>
BugsJustFindMe超过 6 年前
Dear MBTA CTO, why isn&#x27;t this on the MBTA website instead of Medium?
评论 #18181320 未加载
评论 #18181073 未加载
cozzyd超过 6 年前
In theory, one should be able to use information about the stop lights to improve the prediction.<p>Anyway, I really would like to see a histogram of the predicted distribution of arrival times. Sometimes I 1-sigma need to make the bus and sometimes I 3-sigma need to make the bus...
评论 #18185564 未加载
vcryan超过 6 年前
My apologies for being such an opportunist, BUT, we are hiring for various engineering and product roles at the moment: <a href="https:&#x2F;&#x2F;jobs.lever.co&#x2F;mbta" rel="nofollow">https:&#x2F;&#x2F;jobs.lever.co&#x2F;mbta</a>
评论 #18181412 未加载
评论 #18181420 未加载