Deeper than Data

Published on April 30, 2024

Paolo Rinelli

Global Head of Product Management

As we live our lives and travel around, data about our movements comes flowing in from sensors, phones, enforcement cameras and connected devices.  


An unprecedented amount of data is now generated every second, which presents immense potential for the mobility sector. However, the raw data only becomes valuable when it is filtered, cleaned, systematized, and then intelligently leveraged to drive decision-making.

Aimsun offers a comprehensive suite of five digital mobility solutions that can assist you at different levels along this process.

Aimsun Insight 

Artificial intelligence (AI) can analyze several months of historical data from different sources to identify patterns and trends. This helps us to understand the recurrent or ‘normal’ behavior of travelers on their habitual trips. However, it can also spot recurring problems in the transportation infrastructure or mobility services, and pinpoint where some mid-term interventions should be planned. This is the focus of Aimsun Insight.

Aimsun Predict 

If we use AI to complement the analysis of historical data with real-time processing of the same data, we will go beyond understanding the current traffic situation (also known as ‘situational awareness’) to being able to see if there is a problem that deserves immediate attention: if there is an abrupt change of conditions at a certain location, chances are that an incident has occurred in the vicinity; if there is a gradual or general change, it is probably due to a special event affecting the demand. If we add short-term prediction to the mix, we can quickly determine whether that gradual change is going to become a problem later, and – this is the important part – we can prevent it from happening rather than solving it once it has occurred. This is the focus of Aimsun Predict.

Aimsun Plus 

Once we have identified a traffic situation where we need to intervene, the following question is, “What do we do?” This is known as “What if” analysis, i.e., What if I divert traffic? What if I activate a ramp meter? Choosing the best option becomes easier if we know in advance what impact each action will have and which one is more effective.

“What if” analysis is the most typical use case for a mobility model, but it will be a struggle if you are depending solely on AI, because you are unlikely to have enough past observations of exactly this type of situation in this location to understand all the necessary correlations.

If Aimsun Insight has helped you to spot a recurring problem and you want to solve it with a mid-term change in the infrastructure or services, you can run simulations of those situations to assess the effect of different interventions and therefore pick the one that performs the best. This is the focus of Aimsun Plus.

Aimsun Start 

What if you don’t have any data? Not a problem. There are still some decisions you can make by building a high-level model based on open-source data. For example, you could create a model using publicly available data like OpenStreetMap (OSM) for the network and General Transit Feed Specification (GTFS) for the public transport services, and then use it to assess the current accessibility of hospitals by public transport.

This model would be fast and economical to build, and able to show us how modifying routes or schedules might improve accessibility. This is the focus of Aimsun Start.

Aimsun Live  

Finally, if you combine real-time big data processing using AI with real-time simulation, you get a comprehensive system that allows you to spot both recurrent and unexpected problems, and to find the best way to mitigate them. A true digital twin for the mobility system, which we call Aimsun Live.

  • Got a question? Get in touch.

    We are here to help!


Cite Aimsun Next

Aimsun Next 24

Aimsun (2024). Aimsun Next 24 User’s Manual, Aimsun Next Version 24.0.0, Barcelona, Spain. Accessed on: April. 16, 2024. [Online].


Aimsun Next 24

@manual {AimsunManual,
title = {Aimsun Next 24 User’s Manual},
author = {Aimsun},
edition = {Aimsun Next 24.0.0},
address = {Barcelona, Spain},
year = {2024. [Online]},
month = {Accessed on: Month, Day, Year},
url = {},

Aimsun Next 24

T1 – Aimsun Next 24 User’s Manual
A1 – Aimsun
ET – Aimsun Next Version 24.0.0
Y1 – 2024
Y2 – Accessed on: Month, Day, Year
CY – Barcelona, Spain
PB – Aimsun
UR – [In software]. Available: