{"id":27207,"date":"2014-10-22T15:10:40","date_gmt":"2014-10-22T13:10:40","guid":{"rendered":"https:\/\/www.rudebaguette.com\/?p=27207"},"modified":"2019-04-26T18:30:40","modified_gmt":"2019-04-26T16:30:40","slug":"qucit-launches-worlds-first-bikeshare-predictive-api","status":"publish","type":"post","link":"https:\/\/www.rudebaguette.com\/en\/2014\/10\/qucit-launches-worlds-first-bikeshare-predictive-api\/","title":{"rendered":"Qucit launches world’s first bikeshare predictive API"},"content":{"rendered":"

\"Vcub<\/a>Bordeaux-based big data startup Qucit<\/a> released this month the world\u2019s first bikeshare predictive API. It is tightly integrated in iPhone and Android app La Bonne Station<\/a> (the new iPhone version was released yesterday).<\/p>\n

The app uses the API to power a visualization of predicted bike availability over 12 hours in the future, at any given station of Bordeaux\u2019s public bikes network. The technology behind the API comes from 3 years of Research & Development effort and will continue its development in collaboration with the Labri<\/a> and the IMB<\/a> research institutes in Bordeaux. It is based on custom machine learning techniques applied to 4 years of historical data on bikeshare usage, enriched with additional contextual data such as weather conditions.<\/p>\n

Predictive apps for a smart city<\/h2>\n

\"VcubLa Bonne Station<\/a> is an app (available in French and in English) that is edited by Keolis, the public transport operator in Bordeaux. The new predictive functionality has been largely promoted by Keolis as they\u2019ve put promotional seat covers on bikes all over the city.<\/p>\n

In a previous article, we saw how predictive technology was being used in connected objects<\/a>. This new app by Qucit and Keolis is a great example of how predictive apps are also being adopted by end users in their daily lives. It addresses two major problems for those who rely on public bikes for transportation: arriving at\u00a0an empty station when on foot, and arriving at a full station when on a bike. Users can now anticipate and directly go to the right station \u2014 hence the name \u201cla bonne station\u201d in French!<\/p>\n

What would be even cooler would be to have an integration with Snips\u2019 Pocket Brain<\/a> (another French startup) which will predict when you need the bike app \u2014 and potentially predict where you\u2019re going. Speaking of this, Uber recently published a blog post in which they explained how they manage to predict a user\u2019s destination address<\/a> with 74% accuracy.<\/p>\n

Another important aspect of Qucit\u2019s technology is its \u201csmart city\u201d impact. Qucit works\u00a0in close collaboration with Effia, Keolis\u2019 subsidiary which deals with the maintenance of the bikes network. They\u2019re looking at ways to improve load balancing, performed by maintenance trucks that move bikes around the city.<\/p>\n

\"Velib<\/p>\n

An idea could be to equip staff with tablets that leverage the predictive API to anticipate bike usage and to better decide where maintenance\/load-balancing trucks should go \u2014 before stations become empty or full. This could both improve maintenance\u2019s operations and the end-user experience.<\/p>\n

These days, Qucit is also monitoring calls to its API in order to get insights into how the predictive feature is being used: which requests are made, how far in advance, how far from the current position of the user, etc.<\/p>\n

Future challenges<\/h2>\n

To me, the logical next step for the company would be to replicate what they\u2019ve done in Bordeaux to other cities that are also operated by Keolis. Hopefully they will also be able to bring the technology to Paris\u2019 velibs soon (operated by JC Decaux). The current revenue model mixes a fixed fee for setting up the API and a recurring fee for access to the API. If Qucit decides to focus on replicability and scaling, I\u2019m guessing they should be able to lower the setup fee and to transition to a recurring model.<\/p>\n

On a technical aspect, they may need to keep updating their predictive models since people\u2019s habits may change, as more of them will adopt the new predictive feature. Let me explain. The current models assume that, in any given context, users\u2019 behavior is fixed. Overall, it\u2019s probably true that behavior hasn\u2019t changed much since the predictive feature came out. But when adoption reaches a critical level, this assumption won\u2019t be reasonable any more. Consider this example: if many users ask for predictions of available bikes at a given station A, and predictions say there will be none at A but plenty at next station B, then all these users will go to B instead of A; as a consequence, there will be more bikes available at A than predicted, and less at B.<\/p>\n

This won\u2019t be a problem at first, but when the predictive app reaches a critical mass of users, Qucit may need to transition from predictive to prescriptive<\/em>: instead of telling users what\u2019s going to happen, they could recommend them what to do (i.e. they will just tell you which station to go to).<\/p>\n

Qucit (for \u201cQuantified Cities\u201d) was founded a year ago by CEO Dr Rapha\u00ebl Cherrier, a former physics lecturer and researcher at ENSAM. The startup now counts 7 people, it is self-funded and it has received grants from Bpifrance for being a laureate of the Concours National d\u2019Aide \u00e0 la Cr\u00e9ation d\u2019Entreprises Innovantes<\/a>\u00a0[in French] and of the Concours Mondial de l\u2019Innovation<\/a> (\u201cworldwide innovation challenge\u201d) in which any company \u2014 big or small \u2014 that is based or has a subsidiary in France can compete.<\/p>\n

If you\u2019re interested in finding out more about predictive APIs and predictive apps, check out the\u00a0PAPIs.io<\/a>\u00a0conference\u00a0in Barcelona on 17\u201318 November 2014.\u00a0Qucit and other innovative companies will be showcasing their technology<\/a>. Use discount code RBPAPIS to get 20% off on registration.<\/a><\/em><\/p>\n","protected":false},"excerpt":{"rendered":"

Bordeaux-based big data startup Qucit released this month the world\u2019s first bikeshare predictive API. It is tightly integrated in iPhone and Android app La Bonne Station (the new iPhone version was released yesterday). The app uses the API to power a visualization of predicted bike availability over 12 hours in the future, at any given<\/p>\n","protected":false},"author":77,"featured_media":27208,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"subtitle":"","footnotes":""},"categories":[113],"tags":[],"class_list":["post-27207","post","type-post","status-publish","format-standard","has-post-thumbnail","category-finance"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.rudebaguette.com\/en\/wp-json\/wp\/v2\/posts\/27207","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.rudebaguette.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.rudebaguette.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.rudebaguette.com\/en\/wp-json\/wp\/v2\/users\/77"}],"replies":[{"embeddable":true,"href":"https:\/\/www.rudebaguette.com\/en\/wp-json\/wp\/v2\/comments?post=27207"}],"version-history":[{"count":0,"href":"https:\/\/www.rudebaguette.com\/en\/wp-json\/wp\/v2\/posts\/27207\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.rudebaguette.com\/en\/wp-json\/wp\/v2\/media\/27208"}],"wp:attachment":[{"href":"https:\/\/www.rudebaguette.com\/en\/wp-json\/wp\/v2\/media?parent=27207"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.rudebaguette.com\/en\/wp-json\/wp\/v2\/categories?post=27207"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.rudebaguette.com\/en\/wp-json\/wp\/v2\/tags?post=27207"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}