Developing a Simulated Automotive Marketing Software with ChatBot Feature

Assignment Report
Abstract: The need for automation is a serious demand in the marketing platform. Nowadays,
every activity is implemented in a smart way with trending technology. Integrating this
automation in an API is the crucial objective. Some trending features like simulating
conversations with humans and artificially derived responses are to be integrated. Although
“Watson”, which is an IBM super computer to generate system responses using AI technique,
exists, comparing human generated responses with those responses and finally deriving analysis
for choosing exact response is an additional feature that will be integrated. “ActiveDemand” and
“Mautic” are also marketing software which is lagging in this chatBot feature. Mining
mechanism to analyze data content is a challenging issue.
Key words: ChatBot, ActiveDemand, Mautic, API.
Problem Domain and Research questions:
To develop simulated automotive marketing software is our objective. This software is used to
provide the user with an ease to understand the features in it and lucidness in performing each
activity. Each activity integrated in the software must be concise with the stepwise flow diagram
so that the customer shall know in what stage is going presently.
Apart from searching for a product and its price, a smart feature to analyze the present
marketing situation can be performed in the software driven tool. This analysis can be useful to
the customer to trigger a decision whether to buy or not.
Other interesting and trending feature for decision making involves some formal
conversation with marketing experts who will guide to rely on a particular decision. This feature
is known as chatBot. Sometimes customers can go for system evaluated responses to seek an
advice upon making particular decision.
Analyzing tool is required for comparing the expert responses and system generated
responses is provided to the customer. This tool outputs the probability ratio of the responses and
the highest ratio will be the winner.
Research questions: Upon understanding the problem, immediately some questions will be
triggered. Some of the questions regarding the feature extraction are as follows:
1) On what basis, present marketing conditions can be analyzed?
Description: Examining whether the purchase of a product in a particular marketing environment
is desirable or not. This pre analysis will help in the sustainability of the product. The marketing

situation analysis can be done by carefully observing the product stage and its maturity rate. So
this question relies on what basis or on which survey reports the products maturity rate can be
known and up to what extent it is correct?
2) In what way system generated responses will be different from the expert responses?
Description: System generated responses will be pure based on supervised learning mechanism
which is a part of artificial intelligence. The system itself has the capability to analyze the query
from the customers and present appropriate responses. Here the question is in what mechanism
the system is trained so as to generate its own responses.
3) How to compare two sets of responses?
Description: The comparison is done by considering the system and human generated responses
and finally predicts the responses with highest probability. Here, the question is on what
reference the two responses are compared against each other and what is the logic behind it.
Chatbot: As mentioned earlier, ChatBot is used to conduct a conversation with humans through
some protocol. A Chatbot is a computer program that simulates human conversation through
voice commands or text chats or both. Chatbot, short for Chatterbot, is an Artificial Intelligence
(AI) feature that can be embedded and used through any major messaging applications.
A Chatbot is an automated program that interacts with customers like a human would and
cost little to nothing to engage with. Chatbot attend to customers at all times of the day and week
and are not limited by time or a physical location. This makes its implementation appealing to a
lot of businesses that may not have the man-power or financial resources to keep employees
work around the clock.
A Chatbot works in a couple of ways: set guidelines and machine learning. A Chatbot that
functions with a set of guidelines in place is limited in its conversation. It can only respond to a
set number of requests and vocabulary, and is only as intelligent as its programming code. An
example of a limited bot is an automated banking bot that asks the caller some questions to
understand what the caller wants done. The bot would make a command like “Please tell me
what I can do for you by saying account balances, account transfer, or bill payment.” If the
customer responds with "credit card balance," the bot would not understand the request and
would proceed to either repeat the command or transfer the caller to a human assistant.
A Chatbot that functions through machine learning has an artificial neural network
inspired by the neural nodes of the human brain. The bot is programmed to self-learn as it is
introduced to new dialogues and words. In effect, as a Chatbot receives new voice or textual
dialogues, the number of inquiries that it can reply and the accuracy of each response it gives
increases. Facebook has a machine learning Chatbot that creates a platform for companies to
interact with their consumers through the Facebook Messenger application. Using the Messenger
bot, users can buy shoes from spring, order a ride from Uber, and have election conversations
with the New York Times which used the Messenger bot to cover the 2016 presidential election

between Hilary Clinton and Donald Trump. If a user asked the New York Times through his/her
app a question like “What’s new today?” or “What do the polls say?”, the bot would reply to the
request.
Chatbots are used in a variety of sectors and built for different purposes. There are retail
bots designed to pick and order groceries, weather bots that give you weather forecast of the day
or week, and simply friendly bots that just talk to people in need of a friend. The fintech sector
also uses Chatbots to make consumers’ inquiries and application for financial services easier. A
small business lender in Montreal, Thinking Capital, uses a virtual assistant to provide customers
with 24/7 assistance through the Facebook Messenger. A small business hoping to get a loan
from the company need only answer key qualification questions asked by the bot in order to be
deemed eligible to receive up to $300,000 in financing.
Working of Chatbot:
At first, Chatbot can look like a normal app. There is an application layer, a database and APIs to
call external services. In a case of the Chatbot, UI is replaced with chat interface. While Chatbots
are easy to use for users, it adds complexity for the app to handle.
There is a general worry that the bot can’t understand the intent of the customer. The bots are
first trained with the actual data. Most companies that already have a Chatbot must be having
logs of conversations. Developers use that logs to analyze what customers are trying to ask and
what does that mean. With a combination of Machine Learning models and tools built,
developers match questions that customer asks and answers with the best suitable answer.
How is the Chatbot trained?
Training a Chatbot happens at much faster and larger scale than you teach a human. Humans
Customer Service Representatives are given manuals and have them read it and understand.
While the Customer Support Chatbot is fed with thousands of conversation logs and from those
logs, the Chatbot is able to understand what type of question requires what type of answers.
How does the Chatbot learn after it is live?
Once the Chatbot is ready and is live interacting with customers, smart feedback loops can be
implemented. During the conversation when customers ask a question, Chatbot smartly give
them a couple of answers by providing different options like “Did you mean a, b or c”. Those
way customers themselves matches the questions with actual possible intents and that
information can be used to retrain the machine learning model, hence improving the Chabot’s
accuracy.
Despite, there are limitations in place assuring that the model should not change based on new
replies where users are not driving the bot in right direction. Chatbot will also not just rephrase

what the people say in the chat but it is indeed taught to answer things that the bot’s owner wants
it to answer.
How Chatbots actually work?
The Chatbots work by adopting 3 classification methods:
1) Pattern Matchers:
Bots use pattern matching to classify the text and produce a suitable response for the customers.
A standard structure of these patterns is “Artificial Intelligence Markup Language” (AIML).
2) Algorithms
For each kind of question, a unique pattern must be available in the database to provide a suitable
response. With lots of combination on patterns, it creates a hierarchical structure. We use
algorithms to reduce the classifiers and generate the more manageable structure. Computer
scientists call it a “Reductionist” approach- in order to give a simplified solution, it reduces the
problem.
Multinomial Naive Bayes is the classic algorithm for text classification and NLP. For an
instance, let’s assume a set of sentences are given which are belonging to a particular class. With
new input sentence, each word is counted for its occurrence and is accounted for its commonality
and each class is assigned a score. The highest scored class is the most likely to be associated
with the input sentence.
3) Artificial Neural Networks
Neural Networks are a way of calculating the output from the input using weighted connections
which are calculated from repeated iterations while training the data. Each step through the
training data amends the weights resulting in the output with accuracy.
As discussed earlier here also, each sentence is broken down into different words and each word
then is used as input for the neural networks. The weighted connections are then calculated by
different iterations through the training data thousands of times. Each time improving the
weights to making it accurate. The trained data of neural network is a comparable algorithm
more and less code. When there is a comparably small sample, where the training sentences have
200 different words and 20 classes, then that would be a matrix of 200×20. But this matrix size
increases by n times more gradually and can cause a huge number of errors. In this kind of
situations, processing speed should be considerably high.