Monday, June 23, 2008
A Semantic Web Architecture for Advocate Agents to Determine Preferences and Facilitate Decision Making
The main motivation of applying these personalized agents is that they can complement the cognitive limitations of the human mind, and therefore facilitate the decision making process to, reduce information overload (bounded rationality), increase work efficiency (i.e. speed up real-time managerial decisions), increase productivity (cost savings and ROI), increase solution (product or service) quality. Besides these tangible benefits, there are also intangible benefits, e.g. greater customer and employee satisfaction. In order to do this, these agents need to work effectively and efficiently with the human user. Meaning that the agent must learn the human user's interests, habits and preferences (as well as those of their communities). In an online retail example, recommendations can be given as to what to buy (product-brokering) and from whom to buy (merchant-brokering), based on customer criteria.
Agents and the human work in a bi-directional way through the interface called: Economic Dashboard.
"You cannot manage what you do not measure"
"What gets watched, gets done."
These statement demonstrate what the Economic Dashboard is, an "Organizational Magnifying Glass" – to focus the work of employees so everyone is going in the same direction! It business people: (1) Monitor, (2) Analyze, (3) Manage, (4) and Communicate and give feedback to the agent.
In order to work with the Economic Dashboard at all of the different organizational levels, these Economic dashboard has three types that relate to Business Intelligence:
Strategic BI: Achieve long-term organizational goals
Tactical BI: Conduct short-term analysis to achieve strategic goals
Operational BI: Provide a decision-making environment that reduces the latency between the time a significant business event happens and the business' ability to react to it.
In order to bring these personalized results, and work with the personalized results in the Economic Dashboard preferences are elicitated. Preference elicitations is the central concept of decision making and is fundamental for the analysis of human choice behavior, since people have different preferences for different roles. There are four methods or preference elicitation: (1) Questionnaire, which define roles, areas, objectives, and tasks; (2) Implicit feedback through user observation through browser extension (Piggy Bank, etc.), (3) Explicit user feedback through economic dashboard, and none intrusive sidebar in browser window, and (4) Business and Social Networks (Professional (intra company e.g. IBM, Linkedin, Plaxo, etc.) Personal (Facebook, Hi5, Hyves, etc.).
These preferences are saved in RDF stores, which allows the best abilities to apply Semantic Web agents.
In conclusion, this paper demonstrates the feasibility of Advocate Agents by presenting an architecture that integrates current technologies, such as Enterprise Service bus, XML, RDF, and machine learning techniques into a unique system and demonstrating that all the components of Advocate Agents can be built from already existing methods and elements.
After the presentation a discussion was held.
Monday, June 16, 2008
I have been doing a great deal of research on information dashboard design in the last few months for a customer.
There are two resource I would like to make sure our group is well aware of:
Inforamtion Dashboard Design by Stephen Few
Performance Dashboards by Wayne Eckerson
These books each take a different approach to dashboard design. The Few book is more in line with the Tufte visualization theory. The Eckerson is more along the line of applying the theory of the balanced scorecard (figureing out what to measure).
To be successful we will need to create high-quality monitoring and feedback tools between complex agents and non-technical users. AA dashboard could be its own sub-project.
Tuesday, March 11, 2008
Normally the traveler has a set of parameters that frame their travel needs. Instead of entering these over and over, once per search, imagine defining them once, and asking an agent (of the software variety) to begin searching for results that meet your specifications. This seems so obvious you may wonder why it hasn't happened already. The answer is that the current leaders in online travel depend on you visiting their site. Advertisers cannot target software agents, they want real eyeballs on their ads. This Spring I'll be blogging about software agents and online travel, and what needs to occur for that to become a viable way to dream, plan, and purchase travel on the internet. In the mean time, I have taken a stab at what technologies may enable agent based travel search.
Tuesday, November 27, 2007
We hope to see you in
Friday, November 23, 2007
Wan Y., Menon S. & Ramaprasad A. , A classification of product comparison agents. Communications of the ACM, August 2007. A review of this article can be at LARGE
I list below different types of PCA and their real life realization:
Production Differentitation PCA:
http://pricescan.com/ -- often biased to one brand in one particular category
Product Evaluation PCA:
Consumer Preference Identification PCA:
http://www.shopping.com -- (rebranded from dealtime.com) close-coupled agent design that integrates different PCAs into its architecture -- while you start searching it gives you product suggestions, an advocate agent would give you products related to your preferences since it got to know you over time
An aggregate of the 3 main PCAs with social tagging and customer reviews
Refine as you type comparison shopping agents:
Sunday, November 18, 2007
I strongly believe that information is the key to the commerce world. For agents to be provide useful capabilities, they need to be information-aware. To make them information aware, we need
- Information architecture: The information management will provide metadata so the information can be discovered.
- Semantic web: The Semantic web will extend the traditional metadata to the next level to make sure that agents can find the most relevant information
- SOA for Data: This covers using web services to decouple agents from information sources. I prefer using REST, when possible, because it is simple and is based on WWW standards.
In addition to above areas, I believe that research in agents can also benefit from work in data mining.What do you think?