Decision Support Systems

College of Computing and Informatics

Module 11
Chapter 12: Knowledge Systems: Expert
Systems, Recommenders, Chatbots, Virtual
Personal Assistants, and Robo Advisors

Analytics, Data Science, & Artificial Intelligence

Systems For Decision Support

This Presentation is mainly dependent on this textbook

Contents
o12.2 - Expert Systems and Recommenders

o12.3 - Concepts, Drivers, and Benefits of Chatbots

o12.4 - Enterprise Chatbot

o12.5 - Virtual Personal Assistants

o12.6 - Chatbots as Professional Advisors (Robo Advisors)

o12.7 - Implementation Issues

Weekly Learning Outcomes
1.Describe recommendation systems, expert systems and chatbots

2.Understand the drivers and capabilities of chatbots and their use

3.Describe virtual personal assistants and their benefits and describe the use of chatbots as advisors

4.Discuss the major issues related to the implementation of chatbots

 Required Reading
 Chapter 12: “Knowledge Systems: Expert Systems, Recommenders, Chatbots, Virtual
Personal Assistants, and Robo Advisors” from “Analytics, Data Science, & Artificial
Intelligence: Systems for Decision Support”.

Recommended Reading
 Big Data: What it is and why it matters. SAS.
https://www.sas.com/en_sa/insights/big-data/what-is-big-data.html
Recommended Video
 The future of cloud data analytics (2020, Oct 8). [Video]. YouTube
https://www.youtube.com/watch?v=1mQ8VtxIAjk
Week 11
Chapter 12:Knowledge Systems: Expert
Systems, Recommenders, Chatbots, Virtual
Personal Assistants, and Robo Advisors
12.2 Expert Systems and Recommenders
• Basic Concepts of Expert Systems (ES)

• Structure and Process of ES

• Limitations of ES

• New generation of ES

• Recommendation Systems
Basic Concepts of Expert
Systems (ES)
• A category of autonomous decision systems (the earliest applications of AI).

• Started in 1960s by research institutions (e.g., Stanford University, IBM) and was adopted
commercially in 1980s.

• Expert Systems - is a computer-based system that emulates decision making and/or problem
solving of human experts. These decisions and problems are in complex areas (e.g., diagnosing a
problems)
• ES objective is to transfer the expertise from experts to a machine  to enable nonexperts to
make decisions and solve problems that usually require expertise.

• Focus on decisions and problems in narrowly defined domains that require expertise to solve
 E.g. making small loans, providing tax advice, analyzing reasons for machine failure

• Classical ES use “what-if-then” rules for their reasoning.

Basic Concepts of Expert
Systems (ES)
EXPERTS - person who has the special knowledge, judgment, experience, and skills
to provide sound advice and solve complex problems in a narrowly defined area.
 Decision performance and the level of knowledge a person has are typical criteria used to
determine whether a particular person is an expert as related to ES.

Human experts are typically 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 (i.e., going outside the general norms) if necessary.
•Determining relevance and associations.
Basic Concepts of Expert
Systems (ES)
EXPERTISE - The extensive, task-specific knowledge that experts possess. It is associated
with a high degree of intelligence and learning from past successes and mistakes.

•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. This
includes:
 explicit knowledge: such as theories learned from a textbook or a classroom
 implicit knowledge: gained from experience.

Types of experts’ knowledge 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.
Basic Concepts of Expert
Systems (ES)

Expertise often includes the following characteristics

•It is usually associated with a high degree of intelligence, but it is not always as-
sociated 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.
Characteristics and
Benefits of ES
Benefits of Expert Systems (ES)
•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 (e.g., 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.
Characteristics and
Benefits of ES
Typical Areas for ES Applications
•Finance (investments, credit, and financial reports, …).
•Data processing (planning, equipment selection, equipment maintenance,…).
•Marketing (customer relationship management, market research and analysis,
…).
•Human resources (planning, performance evaluation, staff scheduling, ...).
•Manufacturing (e.g., production planning, complex product configuration, …).
•Homeland security (e.g., terrorist threat assessment).
•Business process automation (desk automation, call center management, …).
•Healthcare management.
•Regulatory and compliance requirements.
•Web site design.
Structure and Process
of ES
• Development Environment
 ES developer loads the knowledge-base with
appropriate representation of expert knowledge.
• Consultation Environment
 Used by nonexpert to obtain advice and solve
problems using the expert knowledge embedded
into the system
Major Components of ES
• Knowledge acquisition
• Knowledge Base (a.k.a repository)
• Knowledge representation
• Inference Engine
• User Interface General Architecture of Expert Systems
• Explanation subsystem and knowledge-refining
system.
Limitations of ES
Classical type of ES is disappearing despite benefits, because:
1.knowledge acquisition from human experts very expensive
2.Acquired knowledge needed to be updated frequently at a high cost.
3.The rule-based foundation are not robust and not too reliable or flexible
and could have too many exceptions to the rules.
4.The rule-based user-interface needed to be supplemented (e.g., by voice
communication, image maps). This could make ES too cumbersome.
5.The reasoning capability of rule-based technology is limited compared to
use of newer mechanisms such as those used in machine learning.
New generation of ES based on machine learning algorithms and
other AI technologies are deployed to create better system
New generation
of ES
Three major AI types of applications:
• Chatbots.
• Virtual personal assistants.
• Robo advisors.

Other AI technologies that perform similar activities:

• IBM Watson (some of its advising capabilities are similar to those
of ES but are much superior).

• Recommendation system (a newer variations that use machine

learning and IBM Watson Analytics).
Recommendation
Systems
• knowledge system for recommending one-to-one targeted products or
services (a.k.a recommendation engine).
 It tries to predict the importance (rating or preference) that a user will attach to
a product or service. Once the rating is known, a vendor knows users’ tastes
and preferences and can match and recommend a product or service to the
user.
 The recommendations are typically given in rank order.
• Recommendation system uses several AI technologies to provide
personalized recommendations.
• Online recommendations are preferred by many people over regular
searches, which are less personalized, slower, and sometimes less accurate.
• Top applications areas: movies, music, and books, systems for travel,
restaurants, insurance,…
Benefits Of Recommendation
Systems

Using recommendation systems may result in substantial benefits both to buyers

and sellers.
Benefits to customers
Personalization They receive recommendations that are very close to fulfilling what they like or need. This depends, of course,
on the quality of the method used.
Discovery They may receive recommendations for products that they did not even know existed but were what they really
need.
Customer satisfaction With repeated recommendations tends to increase.
Reports Some recommenders provide reports and others provide explanations about the selected products.
Increased dialog with sellers Because recommendations may come with explanations, buyers may want more interactions with the sellers.
Benefits to sellers
Higher conversion rate With personalized product recommendations, buyers tend to buy more.
Increased cross-sell Recommendation systems can suggest additional products. E.g., Amazon.com shows other products that
“people bought together with the product you ordered.”
Increased customer loyalty As benefits to customers increase, their loyalty to the seller increases.
Enabling of mass customization This provides more information on potential customized orders.
 Recommendation
Systems
• Two methods for building recommendation systems are are collaborative filtering and
content-based filtering.

Collaborative filtering Content-based filtering

• Builds a model that summarizes the past behavior of • Allows vendors to identify preferences by the attributes of the
shoppers (browsing, purchase, rating). product(s) that customers have bought or intend to buy.

• Considers what shoppers with similar profiles bought • The vendor recommends to customers products with similar
and how they rated their purchases. attributes (Knowing product preferences).

• Uses AI algorithms to predict the preference of both old • E.g., the system may recommend a text-mining book to a
and new customers. Then, the computer program makes customer who has shown interest in data mining, or action
a recommendation. movies after a consumer has rented one in this category.

• Several other filtering methods exist (e.g., rule-based filtering and activity-based
filtering).
12.3 CONCEPTS, DRIVERS, AND BENEFITS OF
CHATBOTS
Chatbots
• The world is now infested with chatbots – 60% of millennials have already used them
(Knight, 2017).
• Chatbot - A computerized service that enables easy conversations between humans and
humanlike computerized (robots, image characters, or sometimes over the Internet) in
writing, voice or images. Conversations frequently involve short questions and answers
and are executed in a natural language.
• Used primarily for information search, communication and collaboration, and rendering
advice in limited, specific domains.

Chatbot Evolution
 Chatbots originated decades ago.
 Eliza first Q&A chatbot, it is simple ES that enabled machines to answer questions posted by users.
 Since 2000, more and more capable AI machines for Q&A dialogs have been developed.
 Around 2010, conversational AI machines were named chatbots and later were developed into virtual
personal assistants, championed by Amazon’s Alexa.
Chatbots
• Chatbots contain a knowledge-base (e.g., rule- based) and a natural
language understanding capability, in order to converse with a human.
 Knowledge bases are updated today in the “cloud” in a central location.
 The stored knowledge is matched with questions asked by users.
• To understand unstructured dialog intelligent chatbots are equipped
with NLPs.
 Advanced chatbots can also understand human gestures, cues, and voice variations.

• Learning chatbots gain more knowledge with their accumulated

experience.
• Chatbots are used for many different tasks (e.g., education, banking, insurance,
retail, travel, healthcare, and customer experience,…).
 The service is often available on messaging services such as Facebook Messenger or WeChat,
and on Twitter.
Chatbots
Types of Bots – according to their capabilities:
 Regular bots: conversational intelligent agents that do simple, repetitive, tasks (e.g., showing customers their
bank’s debits)
 Chatbots: stimulate conversations with people.
 Intelligent bots: have a knowledge base that is improving with experience (e.g., Alexa, some robo advisors).

Drivers use of Chatbots and Benefits

Drivers Benefit
• The need to cut costs. • Providing superb and economic customer service and
• The increasing capabilities of AI, especially NLP and conducting market research.
voice technologies. • Its use for text and image recognition.
• The ability to converse in different languages. • To facilitate shopping.
• The increased quality and capability of captured • Its support of decision making.
knowledge.
• The push of devices by vendors (e.g., virtual personal
assistants such as Alexa and Google Assistant).
Components of Chatbots and the Process
of Their Use

The major components of chatbots:

•A person (client).

•A computer, avatar, or robot (the AI machine).

•A knowledge base that can be embedded in the

machine or available and connected to the “cloud.”

•A human-computer interface that provides the dialog

for written or voice modes.

•An NLP that enables the machine to understand natural

language.
The process of chatting with chatbots
 Chatbots

Representative Chatbots from around the world

 RoboCoke: This is a party and music recommendation bot created for Coca-Cola
 Kip: This shopping helper is available on Slack (a messaging platform).
 Zoom: an automated virtual assistant, is for everyone in the workplace.
 … and more in the book.

Major categories of chatbots’ applications

 Chatbots for enterprise activities, including communication, collaboration, customer
service, and sales.
 Chatbots that act as personal assistants (virtual personal assistants).
 Chatbots that act as advisors (a.k.a robo advisors), mostly on finance-related topics.
12.4 Enterprise Chatbot

12.5 Virtual Personal Assistants

12.6 Chatbots as Professional Advisors (Robo

Advisors)
Enterprise Chatbots
• Chatbots can fundamentally change the way that business is done both in
external and internal applications.
• The benefits of chatbots to enterprises:
 making dialog less expensive and more consistent.
 interact with customers and business partners more efficiently,
 available anytime 24/27
 can be reached from anywhere.
Reasons for using enterprise bots (Beaver, 2016):
• “AI has reached a stage in which chatbots can have increasingly engaging and human
conversations, allowing businesses to leverage the inexpensive and wide-reaching
technology to engage with more consumers.

• Chatbots are particularly well suited for mobile-perhaps more so than apps. Messaging is
at the heart of the mobile experience, as the rapid adoption of chat app demonstrates’’
• … more on the book.
Examples of Enterprise
Chatbots
Marketing and customer experience:
• Very useful in providing marketing and customer services (e.g., obtaining sales leads,
persuading customers to buy products and services, providing critical information to potential
buyers, optimizing advertising campaigns).
• Using voice and texting can provide personalization as well as superb customer experience.
• Can enable vendors to improve personal relationships with customers and run marketing
campaigns.
• E.g., LinkedIn is introducing chatbots that conduct tasks such as comparing the calendars of
people participating in meetings and suggesting meeting times and places.

Financial Services
• Banking Chatbots can use predictive analytics and cognitive messaging to perform tasks such
as making payments, inform customers about personalized deals.
• Banks’ credit cards can be advertised via chatbots on Facebook Messenger.
• E.g., Citi Bank Chatbot it can answer FAQs about people’s accounts in a natural language.
Service Industries
Healthcare
 Robot receptionists direct patients to departments in hospitals.
 Several chatbots are chatty companions for people who are elderly and sick.
 Chatbots are used in telemedicine; patients converse with doctors and healthcare professionals who
are in different locations.
 Chatbots can connect patients quickly and easily with information they need.
Education
 Chatbot tutors are used in several countries to teach subjects ranging from English to mathematics.
 The chatbot treats all students equally.
 Machine translation of languages will enable students to take online classes in languages other than
their own.
 chatbots can be used as private tutors.
Government
 Chatbots are spreading in government as a new dialog tool for use by the public (Lacheca, 2017).
 E.g., providing access to government information and answering government-related questions.
Travel and Hospitality
 Chatbots are working as tour guides in several countries (e.g., Norway).
 They act as concierges, providing information and personalized recommendations (e.g., about
restaurants), arrange reservations for hotel rooms, meals, and events.
Chatbots Inside
Enterprises
• Companies lately have started to use chatbots to automate tasks for supporting internal
communication, collaboration, and business processes.
Benefit (Newlands (2017a):
 Chatbots can support decision-making activities.
 cut costs
 increase productivity
 assist working groups
 foster relationships with business partners.
Representative examples of chatbot tasks are inside enterprises:
 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.

• Chatbots’ Platform Providers: ChattyPeople, Kudi, Twyla, BM Watson, Microsoft’s Bot

Framework.
Knowledge for Enterprise
Chatbots
• Knowledge for chatbots depends on their tasks.
• Enterprise chatbots operate very similarly to ES except that the interface occurs in a
natural language and frequently by voice.
 For example, the knowledge of Sephora’s bot is specific to that company and its products and is
organized in a Q&A format.

• Most marketing and customer care bots require proprietary knowledge, which is usually
generated and maintained in-house. This knowledge is similar to that of ES.

• Chatbots that are used within the enterprise (e.g., to train employees) may not be
company specific.
 A company can buy the knowledge and modify it to fit local situations and its specific needs (as
is done in ES)
 Newer chatbots use machine learning to extract knowledge from data.
Virtual Personal
Assistants (VPA)
• An emerging type of chatbot is designed as a virtual personal assistant for both individuals
and organizations.
• Major objective is to help people improve their work, assist in decision making, and facilitate
their lifestyle.
 Examples of such assistants are, Apple’s Siri, Google’s Assistant, and Microsoft Cortana.
 A well-known VPA is Amazon’s Alexa that is accessed via a smart speaker called Echo (or other smart
speakers).

• Assistant for Information Search help users conduct a search by voice for information.
 In business situations delegating the search to a machine may save sellers considerable money and make
customers happy by not having to wait for the service.

Knowledge for Virtual Personal Assistants

 knowledge for virtual personal assistants is kept and centrally maintained in the “cloud”.
 So, it become available to millions of users, and need to provide dynamic, updated information (e.g., weather
conditions, news, stock prices).
 Knowledge usually universal and disseminated via a Q&A dialog.
Chatbots as Professional Advisors
(Robo Advisors)
• A special category of virtual personal assistants designed to provide personalized
professional advice in specific domain. Mainly they operate in investment and
portfolio management.

Robo Financial Advisors

 Online providers that offer automated, low-cost, personalized investment advisory
services.
 They use AI algorithms that allocate, deploy, rebalance, and trade investment
products.

Robo Advisors 2.0: several of the fully automated advisors started to add a
human option
(a.k.a the human touch)
• Quality of advice provided by robo advisors depends on their knowledge, the
type of investments involved, the inference engine of the AI machine.
Chatbots as Professional Advisors
(Robo Advisors)
Other Professional Advisors
•Computer operations: To cut costs, major computer vendors (hardware and soft-
ware) try to provide users with self-guides to solve encountered problems.
• Travel: Several companies provide advice on planning future national and
international trips.
• Medical and health advisors: A large number of health and medical care advisors
operate in many countries.
•E.g, Health Tap acts like a medical doctor by providing a solution to common symptoms provided by
patients.
•Florence is a personal nurse available on Facebook Messenger.
• Shopping advisors: act as shopping advisors
•E.g., shopadvisor.com/our-platform, a comprehensive platform that includes three components:
Product intelligence, Context intelligence, Shopper intelligence to help companies attract customers.
• IBM Watson: probably the most knowledgeable virtual advisor.
12.7 Implementation Issues
• Disadvantages and Limitations of Bots

• Quality of Chatbots

• Constructing Bots
Disadvantages and Limitations of
Bots

• Some bots provide inferior performance, at least during their initiation,

making users frustrated.
• Some bots do not properly represent their brand. Poor design may
result in poor representation.
• The quality of AI-based bots depends on the use of complex algorithms
that are expensive to build and use.
• Some bots are not convenient to use.
• Some bots operate in an inconsistent manner.
• Enterprise chatbots pose great security and integration challenges.
Disadvantages and Limitations
of Bots

Technology issues
•Virtual personal assistants have imperfect voice recognition.
 No good feedback system yet for voice recognition systems to
understands the users.
 Voice recognition systems may not know when to do a current task
and need to ask for human intervention.

•Connecting to an NLP system

 Security and connectivity difficulties…

•Multilingual chatbots need to be connected to a machine language

translator.
Quality of Chatbots
• The quality of most Chatbots is not perfect, but improving over time.
• Chatbots that retrieve information for users and are properly programmed can do a perfect
job.
• Bots that serve a large number of people, such as Alexa and Google Assistant, exhibit an
increasing level of accuracy.
Quality of robo advisor
 Major issue when engaging bots is the potential loss of human touch.
 Bots cannot bring empathy or a sense of friendship.
 Solution:
1. Bots should perform only tasks that they are suited to do.
2. They should provide a visible benefit to the customer.
3. Because the bots face customers, the interactions must be fully planned to make sure the
customers are happy.
• Microsoft’s Tay: Twitter-based chatbot that failed and was discontinued by Microsoft.
Constructing Bots

Setting Up Alexa’s Smart Home System

•Alexa is useful in controlling smart homes.
•A six-step process for how to use Alexa in smart homes (Crist ,2017):
1. Get a speaker (e.g., Echo).
2. Think about the location of the speaker.
3. Set up the smart home devices.
4. Sync related gadgets with Alexa.
5. Set up group and scene.
6. Fine-tune during the process.
Constructing Bots

Guide for creating a Facebook Messenger bot

1.Give it a unique name.
2.Give customers guides on how to build a bot and how to converse with it.
3.Experiment in making a natural conversation flow.
4.Make the bot sound smart, but use simple terminology.
5.Do not deploy all features at the same time.
6.Optimize and maintain the bot to constantly improve its performance.
Constructing Bots

Using Microsoft's azure bot service

•Azure is a comprehensive but not a very complex bot builder.
•Its Bot Service provides five templates for quick and easy creation of bots.
Main Reference
 Chapter 12: “Knowledge Systems: Expert Systems, Recommenders, Chatbots,
Virtual Personal Assistants, and Robo Advisors ” from “Analytics, Data Science, &
Artificial Intelligence: Systems for Decision Support”.

Week self-review
exercises
 Application case 12.1 – 12.7 from “Analytics, Data Science, & Artificial Intelligence: Systems for
Decision Support”.

 Getting started with Watson Assistant:

https://cloud.ibm.com/docs/assistant?topic=assistant-getting-started
Thank
You