Everything you need to estimate, model and predict people’s behavioural choices for transport demand and choice modelling
Visual Choice is our bespoke choice modelling software which models people's choices. It offers a comprehensive Windows based graphical user interface, to provide an easy to use environment in which to design and estimate discrete choice models and apply people's choices in real-world predictive models. It is especially tailored to modelling complex hierarchies of nested choices such as are used at the cutting edge in transport demand models. Visual Choice is comprised of the following modules:
Visual Choice Integrated Development Environment (IDE) - the basic interface
Everything you need to visually open a project; develop, add, view, edit models and files. Run your choice models either interactively (where you can check their calculations) or in batch where they can be deployed on any computer and run at a time to suit you. If you have a web connection you can check on your model's run status via the internet. Completely Windows based.
Visual Choice Modelling - to build, apply and run choice models
This embodies a uniquely simple, yet powerful way of applying choice models so that they can be applied to complex hierarchical nesting of choice models such as are needed for detailed transport models. You can graphically design your choice nests and work through their complexities to check them and apply them in your transport model. The choice nest can take individual people, trip ends or matrices to produce people's decisions as trip matrices depending upon the choice hierarchy. The software is fast so is capable of swiftly running complex nests of choices for transport models such as trip frequency, mode, time period, destination, peak spreading and route choices.
Visual Choice Coefficient Estimation - to estimate discrete choice model coefficients
This estimates the coefficients of the logit model utility function using maximum likelihood logit model estimation for the following types of logit model: multinomial, nested, cross nested, mixed, latent class and dogit. Its graphical user interface helps you set up the estimation specification as well as visually select different model types with a variety of features. Model types can be switched in or out with the click of the mouse. It takes as input a file of attributes, another of decisions, a problem specification file and it outputs a log file containing the coefficients, and statistics for the model being estimated.
Visual Choice Stated Preference - to prepare stated preference experimental designs
Discrete choices are sometimes obtained from stated preference or stated choice experiments which can require complex statistical designs. Visual Choice can generate these designs to your specification. The graphical interface helps you set up your choice specification. You then select the type of design (e.g. orthogonal or efficient design), interactions etc. and Visual Choice will give you the design. If you supply a template (or use one of ours), Visual Choice will even output the games for you.
Visual Choice has been used for over 5 years on our projects and we are now releasing it for others to use. Visual Choice integrates with the CUBE software from Citilabs and with our Visual-tm software so you can apply your choice model in a full multi mode transport modelling context. This is a completely new way of building demand models which will revolutionise transport modelling.