Page 171 - Big Data Analytics for Connected Vehicles and Smart Cities

152 Big Data Analytics for Connected Vehicles and Smart Cities The Practical Application of Analytics to Transportation 153

Table 7.5
Candidate Analytics for Performance Management
Candidate Analytics Application Notes
Ease or resistance to travel from Uses movement analytics (smart phone location) and transit
home to health, education, and schedule data to determine the ease or resistance to travel
employment opportunities from essentially residential zones to those zones containing
health, education, and employment opportunities.
Effectiveness of investments and Uses movement analytics and work program data to
matching of investment to problem analyze the effectiveness of investments by comparing
locations before and after characteristics and considering the match
between the location of the investments and the location of
transportation problems
Optimizing the transportation system Uses a combination of crash statistics to characterize the
citywide to minimize accidents current situation and then develop a range of strategies
designed to optimize citywide transportation service delivery
from a safety perspective.
Adjusting the different modes As above but placing a focus on the transfer time or
of transportation to maximize connectivity of different modes.
conductivity required
Price analysis by market segment Uses movement analytics and mode price data to compare
and time of day. Price per passenger, the value proposition offered by different modes.
price per origin/destination pairs.
Value proposition for each passenger
and each trip

7.19 Summary

This chapter provides some information on the practical application of analyt-
ics to transportation. To provide the context for the application of the analytics,
the chapter first identifies a series of departure points for a smart city initia-
tive. These are explained in terms of the elements that comprise the departure
point initiatives and the services that can be delivered by each departure point.
For each departure point, a small selection of candidate analytics are defined
and some advice is provided on the practical application of these analytics to
improving service quality levels for transportation. Note that these are not the
only possible departure points and that this is not intended to be a catalog but
rather a practical exposition of how to apply analytics to transportation within
a smart city environment. Nevertheless, the departure points included are ones
that are likely to be attractive to a city when considering the needs of a smart
city initiative.
Each smart city initiative will likely develop its own set of analytics based
on specific needs. It is further likely that the early analytics for pilot projects
and for proof of concept in the development of business case justifications will
consider the value proposition that the use of each set of analytics will unleash
and the availability of suitable data to support at least the first wave of analy-
sis. This is likely to be an iterative process with lessons learned and practical