KNOWLEDGE SYSTEMS: EXPERT

SYSTEMS, RECOMMENDERS,
CHATBOTS, VIRTUAL PERSONAL
ASSISTANTS, AND ROBO
ADVISORS
Assoc. Prof. Dr. Nurul Hashimah Ahamed Hassain Malim
CMT / CMM 426

Copyright © 2020 by Pearson Education, Inc. All Rights Reserved

LEARNING OBJECTIVES
Describe recommendation systems

Describe expert systems

Describe chatbots

Understand the drivers and capabilities of chatbots and their use

Describe virtual personal assistants and their benefits

Describe the use of chatbots as advisors

Discuss the major issues related to the implementation of chatbots

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
CONCEPTS OF EXPERT SYSTEMS (E S)
▪ ES is a computer-based information system
▪ Emulates the decision making and/or problem-solving
abilities of human experts in complex areas
▪ One of the earliest success application areas of AI
▪ Expert systems use started in research institutions in
1960s
▪ Goal – help nonexperts to make decisions and solve
problems that usually require expertise
▪ Works well in narrowly defined domains

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
CONCEPTS OF EXPERT SYSTEMS (E S)

▪ Expert - A person who has the special knowledge, judgment,

experience, and skills to provide sound advice and solve complex
problems in a narrowly defined area.
▪ To be called an expert, one must be able to solve a problem and
achieve a performance level that is significantly better than an
average person
▪ An expert at one time or in one region may not be an expert in
another time or region.
▪ E.g., a legal expert in New York is not a expert in Beijing

▪ Experts have expertise that can help solve problems and explain
certain obscure phenomena only within a specific domain

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
CONCEPTS OF EXPERT SYSTEMS (E S)

▪ Typically, human experts are capable of doing the following:

▪ Recognizing and formulating a problem
▪ Solving a problem quickly and correctly
▪ Explaining a solution
▪ Learning from experience
▪ Restructuring knowledge
▪ Breaking rules and norms, if necessary
▪ Determining relevance and associations

▪ Can ES do these? Can a machine help a nonexpert perform

like an expert?
▪ Real experts are rare and hard to find

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
CONCEPTS OF EXPERT SYSTEMS (E S
▪ Expertise - The extensive, task-specific knowledge that
experts possess.
▪ The level of expertise determines the success of a
decision made by an expert.
▪ Expertise is often acquired through training, learning,
and experience in practice.
▪ Expertise includes explicit knowledge, such as theories
learned from a textbook or a classroom and implicit
knowledge gained from experience.

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
CONCEPTS OF EXPERT SYSTEMS (E S)
▪ Knowledge types (expertise) used in ES applications
▪ Theories about the problem domain
▪ Rules and procedures regarding the general problem
domain
▪ Heuristics about what to do in a given problem situation
▪ Global strategies for solving of problems amenable to
expert systems
▪ Meta knowledge (i.e., knowledge about knowledge)
▪ Facts about the problem area

▪ These types of knowledge enable experts to make better

and faster decisions than nonexperts.

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
CONCEPTS OF EXPERT SYSTEMS (E S)
▪ Expertise often includes the following characteristics:
▪ It is usually associated with a high degree of
intelligence, but it is not always associated with the
smartest person
▪ It is usually associated with a vast quantity of
knowledge
▪ It is based on learning from past successes and
mistakes
▪ It is based on knowledge that is well stored,
organized, and quickly retrievable from an expert
who has excellent recall of patterns from previous
experiences.

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
CHARACTERISTICS AND BENEFITS OF E S
▪ ES were use explicitly by hundreds of companies during the
period of 1980 to 2010
▪ Since 2011, the explicit use cases for ES experienced a rapid
decline
▪ Reason - the emergence of better knowledge systems, three
types of which are described in this chapter
▪ The major objective of ES is the transfer of expertise to a
machine.
▪ Then, the expertise will be used by nonexperts.

▪ A typical example of ES use is diagnosis.

▪ Self-diagnosis of computer problems
▪ Diagnosis in medicine – See the example on “Are You
Crazy?”

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
BENEFITS OF E S
▪ Perform routine tasks (e.g., diagnosis, candidate screening, credit
analysis) that require expertise much faster than humans.
▪ Reduce the cost of operations.
▪ Improve consistency and quality of work, reduce human errors.
▪ Speed up decision making and make consistent decisions.
▪ May motivate employees to increase productivity.
▪ Preserve scarce expertise of retiring employees.
▪ Help transfer and reuse knowledge.
▪ Reduce employee training cost by using self-training.
▪ Solve complex problems without experts and solve them faster.
▪ See things that even experts sometimes miss.
▪ Combine expertise of several experts.
▪ Centralize decision making (e.g., by using the “cloud”).
▪ Facilitate knowledge sharing.

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
GENERAL ARCHITECTURE OF AN ES
▪ Consultation Environment
(use of ES via GUI)
▪ Development
Environment
▪ Component of an ES
▪ Knowledge acquisition
(from humans and
others)
▪ Knowledge
representation (if-
then-else rules)
▪ Knowledge base
(knowledge
repository)
▪ Inference engine
(control/search
structure)

▪ User interface 
▪ Justifier/explanation module  Less common
▪ Knowledge refinement system  ES components


Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
WHY THE CLASSICAL E S ARE DISAPPEARING
▪ The use of classical ES are rapidly decreasing for the
following reasons:
1. Issued with acquisition of knowledge from experts
▪ Shortage of real experts and knowledge engineers
2. Need to frequently update acquired knowledge
3. Lack of efficiency and robustness in the rule-based
foundation
4. Need to supplement the rule-based user-interface
(e.g., by voice communication, image maps).
5. The reasoning capability of rule-based technology is
limited compared to use of newer mechanisms such
as those used in machine learning.

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
RECOMMENDATION SYSTEMS
▪ Recommendation system, also known as recommender
system or recommendation engine
▪ Recommending/suggesting one-to-one targeted
products or services
▪ Predict the importance (rating or preference) that a
user will attach to a product or service
▪ Based on the prediction, specific products and
services are recommended to the user
▪ Top applications include movies, music, and books.
However, there are also systems for travel,
restaurants, insurance, and online dating.

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
BENEFITS OF RECOMMENDATION SYSTEMS
▪ Benefits to customer:
▪ Personalization
▪ Discovery
▪ Customer satisfaction
▪ Reports
▪ Increased dialog with seller
▪ Benefits to seller:
▪ Higher conversion rate
▪ Increased cross-sell
▪ Increased customer loyalty
▪ Enabling mass customization

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
METHODS FOR RECOMMENDATION SYSTEMS
▪ Collaborative filtering
▪ Building a model that summarizes the past behavior of
shoppers in a multi-dimensional manner
▪ Makes recommendations on the new customers based on
the similarity to previous shoppers
▪ Uses AI/machine learning to predict the preferences

▪ Content-based filtering
▪ Allows vendors to identify customer preferences by the
attributes of the product(s) that customers have bought
▪ Recommend new products with similar attributes

▪ Several other filtering methods also exists

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
PLEASE WATCH
▪ Recommender System (collaborative filtering, content-based filtering):
▪ [Link]

▪ How Recommender Systems Work (Netflix/Amazon):

▪ [Link]

▪ 26 Content based Recommender Systems:

▪ [Link]

▪ 27 Collaborative Filtering:
▪ [Link]

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
CHATBOTS
▪ Chatbots (chat robots) emerged in the last decade
▪ A computerized service that enables easy
conversations between humans and humanlike
computerized robots or image characters
▪ Some chatbots are equipped with NLP abilities for
better understanding, and some with AI/machine
learning for learning and improving
▪ Chatbot services are often available messaging
services such as Facebook Messenger or WeChat, and
on Twitter

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
TYPES OF BOTS
▪ Regular bots. These are essentially conversational intelligent
agents
▪ They can do simple, usually repetitive, tasks for their
owners, such as showing their bank’s debits, helping them
to purchase goods online, and to sell or buy stocks online.
▪ Chatbots. In this category, we include more capable bots, for
example, those that can stimulate conversations with people.
▪ Intelligent bots. These have a knowledge base that is
improving with experience.
▪ That is, these bots can learn, for example, a customer’s
preferences (e.g., like Alexa and some robo advisors).

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
CHATBOTS
▪ Drivers
▪ Powerful tools to build chatbots
▪ The quality of conversations is improving
▪ Demand for chatbots are increasing (allowing rapid
growth without the need to hire many service personnel)
▪ Helps in appealing to younger customers

▪ Components
▪ A person (client)
▪ A computer, avatar, or robot (the AI machine)
▪ A knowledge base (often stored at the cloud)
▪ A human-computer interface (enabler of the dialog)
▪ NLP that enables machine to “understand” the user

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
PROCESS OF CHATTING WITH A CHATBOTS

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
CHATBOTS DRIVERS AND BENEFITS
▪ The need to cut costs.
▪ The increasing capabilities of AI, especially NLP and voice
technologies.
▪ The ability of conversing in different languages (via machine
translation).
▪ The increased quality and capability of captured knowledge.
▪ The push of devices by vendors (e.g., virtual personal
assistants such as Alexa from Amazon and Google Assistant
from Alphabet).
▪ Its use for providing superb and economic customer service
and conducting market research.
▪ Its use for text and image recognition.
▪ Its use to facilitate shopping and support of decision making.

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
CHATBOTS
▪ Representative Chatbots from Around the World
▪ RoboCoke, Kip, Walnut, Taxi Bot, ShopiiBot, BO.T,
Hazie, Green Card, Zoom, Akita, …
▪ For more, please see [Link]/ and
[Link]/bots/
▪ Major Categories of Chatbots’ Applications
▪ Chatbots for enterprise activities, including
communication, collaboration, customer service, and
sales (such as in the opening vignette)
▪ Chatbots that act as personal assistants
▪ Chatbots that act as advisors, mostly on finance-
related topics
▪ These are explained in the following sections

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
ENTERPRISE CHATBOTS
▪ Chatbots can fundamentally change the way that
business is done. The interest of enterprises in chatbots
▪ Less expensive and more consistent
▪ Mobile friendly (the new trend for new generation)
▪ Chatbots for marketing and customer experience
▪ Improving the customer experience
▪ Examples
▪ LinkedIn
▪ Mastercard
▪ Coca-Cola
▪ Messaging services and Facebook’s chatbots

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
ENTERPRISE CHATBOTS
▪ Enterprise Chatbots: Financial Services
▪ Banking - Chatbots can use predictive analytics and
cognitive messaging to perform tasks such as making
payments, inquiring account details, etc.
▪ Example: POSB of Singapore has an AI-driven bot on
Facebook Messenger
▪ Enterprise Chatbots: Service Industry
▪ Healthcare – robot receptionist, chatty companions,
…
▪ Education – tutors, translators, …
▪ Government – dialog tool for use by the public
▪ Travel and hospitality – tour guides, customer service

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
ENTERPRISE CHATBOTS
▪ Representative examples of chatbot tasks:
▪ Help with project management.
▪ Handle data entry.
▪ Conduct scheduling.
▪ Streamline payments with partners.
▪ Advise on authorization of funds.
▪ Monitor work and workers.
▪ Analyze internal Big Data.
▪ Find discounted and less expensive products.
▪ Simplify interactions.
▪ Facilitate data-driven strategy.
▪ Use machine learning.
▪ Facilitate and manage personal finance.

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
VIRTUAL PERSONAL ASSISTANTS
▪ Assistant for Information Search
▪ If You Were Mark Zuckerberg, Facebook CEO
▪ While Siri and Alexa were in development he
develop his own personal assistant to help him run
his home and his work
▪ Amazon’s Alexa and Echo
▪ Alexa can do many things…
▪ Alexa can be taught/customized for individualized
skills
▪ Amazon Echo, Echo Dot, and Echo Tap
▪ Alexa for Enterprise …

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
VIRTUAL PERSONAL ASSISTANTS
▪ Apple Siri
▪ Siri: Speech Interpretation and Recognition Interface
▪ VIV: developed in 2016, by Dag Kittlaus, the creator of
Siri, as “an intelligent Interface for everything”
▪ Goggle Assistant
▪ Other personal assistants
▪ Microsoft Cortana (Cortana with Bing)
▪ Samsung Bixby
▪ Competition Among Large Tech Companies
▪ Knowledge for Virtual Personal Assistants

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
CHATBOTS AND PROFESSIONAL ADVISORS
(ROBO ADVISORS)
▪ A special category of virtual personal assistants
▪ Designed to provide personalized professional advice
in specific domains, especially in investment and
portfolio management
▪ Evolution of Financial Robo Advisors
▪ Robo Advisors 2.0: Adding the Human Touch
▪ Quality of advice provided by robo advisors?
▪ It depends on their knowledge embedded within
▪ Managing Mutual Funds Using AI

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
CHATBOTS AND PROFESSIONAL ADVISORS
(ROBO ADVISORS)
▪ Other Professional Advisors
▪ Computer operations
▪ Self-guides to solve encountered problems
▪ Travel
▪ planning future national and international trips
▪ Medical and health advisors
▪ Shopping advisors (shopbots)
▪ Example: Smart Assistant Shopping Bots
▪ IBM Watson-based robo advisors

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved
CHATBOTS IMPLEMENTATION ISSUES
▪ Technology issues
▪ Disadvantages and limitations of bots
▪ Inferior performance
▪ Virtual assistants under attack
▪ Quality of Chatbots
▪ Quality of robo advisors
▪ Microsoft’s Tay (Twitter based chatbot)
▪ Constructing Bots
▪ Using Microsoft’s Azure bot service

Copyright © 2020, 2015, 2011 Pearson Education, Inc. All Rights Reserved