Apt Decision Agent

In complex domain spaces, people give minimal/incomplete/incorrect descriptions of what they want. Why?

• They don't know what they really want
• They forgot some crucial piece of information or level of detail
• They lack information that an agent could give them

Computer programs attempt to solve this problem, but they often fail. Why?

• They require decisions before the user has the information to make them
• They often don't incorporate knowledge about the domain in a way that is accessible to the user.
• They don't learn anything about the users' choices or preferences

The Apt Decision Agent:

• Helps the user make decisions in a complex domain space (real estate)
• Helps the user learn about the domain and recall details about choices
• Learns from the user's behavior by observing interactions with the system
• Provides the user with a familiar style of interface which has 'extra' capabilities

How it works:

• The user enters minimal information to start, enough to generate a list of potential apartments.
• While the agent watches, the user chooses desirable or undesirable attribute values from the apartments shown.
• The agent, using its knowledge of the real estate domain, learns the user's preferences, and offers suggestions based on those preferences. Preferences are stored in a profile.
• Through successive iterations, the agent adjusts the user's profile with increasing certainty. The profile can be saved and 'handed off' to negotiation or shopping agents

Some Destinations:

Show presentation (from IUI 2001). Requires Javascript.

Download paper (PDF)

An Apt Decision presentation from summer 2000.