Navigation on this site is not optimized for your browser

Please use a recent version of Google Chrome, Mozilla Firefox, Safari or Microsoft Edge to get the most out of the experience.

Find a modern browser
Hero picture
Blog
news

Blog: Series of Mini-Blogs from the Artificial Intelligence Society of Hong Kong (2)

03/08/2018
  • Asia-Pacific
  • Artificial intelligence
  • Costs
  • Data
  • Decision-making
  • Infrastructure

Series Introduction

Artificial Intelligence (AI) is everywhere these days or at least everyone seems to be talking about it. Not a day goes by without the news of yet another breakthrough, yet another application where AI seems to outperform us humans. 

It should come as no surprise then that people across industries wonder how much of an impact AI is going to have on their respective field and public transport seems to be no exception here. 

While no one can tell for certain what will happen to AI research and application in the coming 5, 10 or 20 years, there certainly is a lot to be learnt from current developments.

When it comes to those developments there are a lot of interesting things to be said about how the face of public transport could and already is changing with the help of AI.

This series is meant to give a brief introduction to how, where and especially why AI can have an impact on public transport.

Entry Two: Resource Allocation Prediction

This term sounds complicated. While it certainly is a challenging task, the basic idea here is simple: How can I use the capabilities of an AI system to predict how to best make use of my available resources?

Applications could include deciding where to deploy security patrols, how many applicants to hire and which train/bus frequency to offer, taking into account what day of the week it is, what time of the day it is and whether special events are happening around the city.

The ‘Predictive’ Part of Resource Allocation Prediction

The key term here is ‘prediction’. We want to predict how to best make use of our resources in future scenarios. The way to do that in modelling is to look at past data and try to detect patterns that will hopefully enable us to better understand future events.

In resource allocation prediction -just like in so many other AI challenges- the key lies in the combination of good data with smart modelling:

Data: What data do I need in order to answer my question and how do I get access to it? Is it even possible to obtain the kind of data that I need and is ‘raw’ data enough or do I need to combine and transform it to succeed? Most often the latter is the case.

In public transport demand prediction for example, it is likely very important to know when major sporting events take place or whether a big demonstration is going to happen downtown this coming weekend. Obviously, the time of day, the day of the week and the month of the year are very important factors as might be the weather.

Modelling: Even the best data does not help much if I do not know how to extract learnings from it.

(Predictive) modelling requires the combination of data analysis/modelling skills and subject matter expertise (SME). It often happens that subject matter experts quickly see things in data that they are very familiar with. Acquiring the same insights from the same data might take non-SMEs significantly longer.

This is not just the case in predictive modeling but all kinds of applications of AI.

What Types of Predictive Modelling are being Used Today?

Predictive modelling has become a cornerstone of AI applications and is already widely used in many industries. There is software that helps police departments predict where crime is likely to occur and electricity providers use it to assess where demand is headed.

Demand prediction could be just as valuable to public transport companies: Predicting when and where demand will increase or decrease can help improve efficiency, customer satisfaction and security.

In terms of security, which public transport provider would not like to be able to accurately predict when and where along their infrastructure security incidents might arise? Where do I send my security staff at any given time? This is not only relevant to customer security but can also help reduce costs if employees are deployed in smart and efficient ways.

So Many Applications

There are quite literally thousands of potential applications of resource allocation prediction in public transport. The key often is co-operation between data experts and SMEs. It is the latter that know better than anyone else where challenges lie and the former should be able to answer if predictive modelling can help solve them.

The blog articles are the writers' opinions and do not necessarily represent UITP perspective or view.
Access
exclusive resources
This website uses cookies

This website uses third-party website tracking technologies to give you the best experience, help us understand and continually improve how the site works, and to display advertisements according to users' interests. You consent to the use of our cookies by continuing to browse this website.

Show Details
Name Description
Core and Analytic Core cookies are essential for the website to function by allowing you to browse the website and use some of its features. Analytic cookies help us analyse how the site is used and allow us to perfect and improve your user experience. These cookies do not collect information that identifies you and are enabled by default.
Name Description
Functional These cookies allow a website to remember the user’s site preferences and choices they make on the site including username, region, and language. The data collected by these cookies are only used in connection with this website and cannot be used to track your browsing on other websites.
Name Description
Advertising These cookies track the surfing behavior of a user to a website and personalise your experience by showing you advertisements, offers, etc. tailored to your interests and preferences.