Chatbot for Access to Stock Market Information
SANTOSH S
M.Tech CNE Dr. B S SHYLAJA
Dr.AIT College Professor
Bangalore, Karnataka Dept. of ISE
shrisanthosh95@gmail.com Dr.AIT
Bangalore, Karnataka
Abstract— This paper describes the usage of chatbot apps
and demonstrates about stock monitor chatbot. Currently,
there are many virtual assistants such as google assistant and
Amazon Alexa, via messaging apps such as Facebook
Messenger or WeChat, or via individual organizations' apps
and websites. In Contrast, we propose the use case of chatbot
apps and their fundamental usage in real-time with help of
artificial intelligence. This paper describes about the software
that analyzes previous stock data of certain companies, with
help of certain parameters that affect stock value. This will also
help us to determine the values that particular stock will have
in near future. This will ensure the Month’s High and Low
with help of data mining algorithms. Stock Market Analysis of
stocks using data mining will be useful for new investors to
invest in the stock market based on the various factors
considered by the software. The stock market includes daily
activities like Sensex calculation, exchange of shares. The
exchange provides an efficient and transparent market for
trading in equity, debt instruments, and derivatives.
Keywords— Artificial Intelligence, Chatbot, Stock Monitor
Chatbot
I. INTRODUCTION
In the field of computer science, artificial
intelligence (AI), sometimes called machine
intelligence, is intelligence demonstrated by
machines, in contrast to the natural intelligence
displayed by humans and other animals.
Computer science defines AI research as the study
of "intelligent agents": any device that perceives
its environment and takes actions that maximize
its chance of successfully achieving its goals.
More specifically, Kaplan and Haenlein define AI
as “a system’s ability to correctly interpret
external data, to learn from such data, and to use
those learnings to achieve specific goals and tasks
through flexible adaptation”. Colloquially, the
term "artificial intelligence" is applied when a
machine mimics "cognitive" functions that
humans associate with other human minds, such
as "learning" and "problem solving".[1]
II. CHATBOT
A chatbot (also known as a smartbot, talkbot, chatterbot,
Bot, IM bot, interactive agent, conversational interface or
artificial conversational entity) is a computer program or an
artificial intelligence which conducts a conversation via
XXX-X-XXXX-XXXX-X/XX/$XX.00 ©20XX IEEE
auditory or textual methods. Such programs are often
designed to convincingly simulate how a human would
behave as a conversational partner, thereby passing the
Turing test. Chatbots are typically used in dialog systems for
various practical purposes including customer service or
information acquisition. Some chatbots use sophisticated
natural language processing systems, but many simpler ones
scan for keywords within the input, then pull a reply with
the most matching keywords, or the most similar wording
pattern, from a database.
The term "ChatterBot" was originally coined by Michael
Mauldin (creator of the first Verbot, Julia) in 1994 to
describe these conversational programs. Today, most
chatbots are accessed via virtual assistants such as Google
Assistant and Amazon Alexa, via messaging apps such as
Facebook Messenger or WeChat, or via individual
organizations' apps and websites. Chatbots can be classified
into usage categories such as conversational commerce (e-
commerce via chat), analytics, communication, customer
support, design, developer tools, education, entertainment,
finance, food, games, health, HR, marketing, news,
personal, productivity, shopping, social, sports, travel and
utilities.[2]
III. CHATBOT SECTION
A. Messaging apps
Many companies' chatbots run on messaging apps like
Facebook Messenger (since 2016), WeChat (since 2013),
WhatsApp, LiveChat, Kik, Slack, Line, Telegram, or simply
via SMS. They are used for B2C customer service, sales and
marketing.[3]
In 2016, Facebook Messenger allowed developers to place
chatbots on their platform. There were 30,000 bots created
for Messenger in the first six months, rising to 100,000 by
September 2017.
Since September 2017, this has also been as part of a pilot
program on WhatsApp. Airlines KLM and Aeroméxico both
announced their participation in the testing; both airlines had
previously launched customer services on the Facebook
Messenger platform.The bots usually appear as one of the
user's contacts, but can sometimes act as participants in a
group chat.
Many banks, insurers, media companies, e-commerce
companies, airlines, hotel chains, retailers, health care
providers, government entities and restaurant chains have
used chatbots to answer simple questions, increase customer
engagement, for promotion, and to offer additional ways to
order from them.
A 2017 study showed 4% of companies used chatbots.
According to a 2016 study, 80% of businesses said they
intended to have one by 2020.
Fig 1. Aeromexico airline chatbot running on Facebook
Messenger, March 2018[3]
1. As part of company apps and websites
Previous generations of chatbots were present on
company websites, e.g. Ask Jenn from Alaska Airlines
which debuted in 2008 or Expedia's virtual customer service
agent which launched in 2011. The newer generation of
chatbots includes IBM Watson-powered "Rocky",
introduced in February 2017 by the New York City-based e-
commerce company Rare Carat to provide information to
prospective diamond buyers.
B. Company internal platforms
Other companies explore ways they can use chatbots
internally, for example for Customer Support, Human
Resources, or even in Internet-of-Things (IoT) projects.
Overstock.com, for one, has reportedly launched a chatbot
named Mila to automate certain simple yet time-consuming
processes when requesting for a sick leave. Other large
companies such as Lloyds Banking Group, Royal Bank of
Scotland, Renault and Citroën are now using automated
online assistants instead of call centres with humans to
provide a first point of contact. A SaaS chatbot business
ecosystem has been steadily growing since the F8
Conference when Facebook's Mark Zuckerberg unveiled
that Messenger would allow chatbots into the app. In large
companies, like in hospitals and aviation organizations, IT
architects are designing reference architectures for
Intelligent Chatbots that are used to unlock and share
knowledge and experience in the organization more
efficiently, and reduce the errors in answers from expert
service desks significantly. These Intelligent Chatbots make
use of all kinds of artificial intelligence like image
moderation and natural language understanding (NLU),
natural language generation (NLG), machine learning and
deep learning.
C. Toys
Chatbots have also been incorporated into devices not
Identify applicable funding agency here. If none, delete this text box.
primarily meant for computing such as toys. Hello Barbie is
an Internet-connected version of the doll that uses a chatbot
provided by the company ToyTalk, which previously used
the chatbot for a range of smartphone-based characters for
children. These characters' behaviors are constrained by a
set of rules that in effect emulate a particular character and
produce a storyline.
IBM's Watson computer has been used as the basis for
chatbot-based educational toys for companies such as
CogniToys intended to interact with children for educational
purposes.
D. Chatbots in Medicine and for Mental Health
According to the Journal of Medical Internet Research,
"Chatbots are [...] increasingly used in particular for mental
health applications, prevention and behavior change
applications (such as smoking cessation or physical activity
interventions)". They have been shown to serve as a cost-
effective and accessible therapeutic agents for indications
such as depression and anxiety. A conversational agent
called Woebot has been shown to significantly reduce
depression in young adults.[3]
IV. Stock Monitor Chatbot
A. OBJECTIVE
In Stock bot, We concentrate with user related to their
queries like what is the particular time to invest? etc., in
order to monitor the current stock trends, we give them
suggestions based on their vision and thoughts we improve
their shares and give more details of what type of shares
they want to start and we also suggest customers in order to
maintain their shares, We suggest do you require any
personal advisor to monitor their shares and many more
with related to stock monitor related work. It also works for
24/7.
B. SCOPE
Stock Market Analysis of stocks using data mining will be
useful for new investors to invest in the stock market based
on the various factors considered by the software.
The stock market includes daily activities like Sensex
calculation, exchange of shares. The exchange provides an
efficient and transparent market for trading in equity, debt
instruments, and derivatives.[5]
Our software will be analyzing Sensex based on the
company's stock value. The stock values of the company
depend on some of the following factors:
1. Dollar value: The fluctuations in the dollar value day by
day will be playing a crucial part in the stock values of
companies (basically I.T based companies) The impact of
dollar values will be different for different companies.
2. Corporate results: This will be regarding the profits or
progress of the company over a span of time say 3 months.
3. Inflation: The overall rise in the price of all the products
which affects purchasing power.
The stock value depends on other factors as well, but we are
taking into consideration only these particular factors.
Stock Bot can be integrated into popular social media
networking sites or particular organization which is working
stock markets and demat account holders. It will save the
conversational time between demat account
holder(customer) and stockbroker. It will enhance the
company work in a simple manner, and help them to
concentrate on other tasks. We can add it for banking
application with added some security feature.
C. FEATURES
• Add or Remove any company and view Multiple graphs •
Upload data without manual feeding by uploading data from
nseindia.com • View Daily, Weekly, Monthly Stock charts
for Technical Stock Analysis • View Daily, Weekly,
Monthly Technical Graphs • Help and Theory regarding
various Technicals in software • User Defined input and
shortlisting as per Moving Average Curve • Shortlisting of
stocks according to various Technical indicators.
• This are the only site selling the Fully Licensed versions of
the Technical Analysis software StocktechTM.
A. Analyzing stock data.
By performing the operation we have obtained stock data
from some companies that affect the Sensex. The data is
from 2nd January 2006 to September 2007. The data has a
date as well as the value of the company's stock at the end of
the trading session of that date.
B. Analyzing the factors.
Based on the results we have to obtain the data in the
same period for the following factors.
1. Dollar value: We will obtain the variation of dollar value
as compared to the rupee.
2. Corporate results: Companies declare their performance
results and profit at the end of each quarter.
3. Inflation: From financial experts, we can obtain an
inflation rate over a period of time.
Based on the results we have to analyze the variations in the
stock value of the companies with respect to these factors
using some data mining algorithms. We will also verify our
results with the results obtained by “DB miner” software.
ChatBOT interface all stock market-related queries and
automating used cases conversation between stocks market
and user, knowledge base search, which improves speed and
accuracy. Integrate into social networking site. Multi-
channel interaction.[14]
Security feature: Bots to verify users via registration
procedure, then OTP is sent through registered Email-Id
before taking any related process.
A technology used: NLP, AI automation tool.
D. FUNCTIONAL REQUIREMENTS
With the help of chatterbot, we implement the chatbot to our
requirement. Chatbots also called as virtual agents and
cognitive agents within Stocks market, AI helps to improve
operational efficiency and creating new stock investors to
start their shares in stock by augmenting human intelligence.
Chatbots are low cost and low-risk entry point for
companies seeking to employ AI in Stock Monitoring
process through prebuilt routines, data models and training.
1. User Interface: The user is required to select which
company is he interested in amongst the various companies
that have been provided.
2. Visual Studio 2010 to Stock Database connectivity: As
communication with the user is performed in C#.net and
data required for processing is in a Database, a connectivity
has to be implemented between the Database and Asp.Net
application
3. Database to DB miner connectivity: Pattern Analysis of
the data in the database has to be performed using various
mining tools provided by Db minor. Hence a connectivity
between the two is required.
Following some functional parameters, we can go for
building chatbot.
1. User Interface is done through a test based or a
combination of GUI and text.
2. Interpretation is done through NLP and AI.
3. The data collected will save all over conversational
details in the .yml file.
4. An action is being carried out having workflow created
by user input can vary depending on input.
5. Integration is done through having layered on top of
existing tech stack with defined interfaces.
6. Client interface can integrate with chat application.
E. LIMITATIONS
Requires an active internet connection, May generate
inaccurate results if data inputted incorrectly
1. In all the approaches which we discussed in this report,
we assumed, whenever we want to make a trade, we are able
to find someone who is willing to make that trade with us
and we get the shares which we are looking for. This is not
true in real time trading. To understand in more detail about
the behaviour of our approaches, we need to test these
models against real-time data.[15]
2. For comparison, we have chosen stocks from various
sectors. However, the behaviour of these indicators may
vary with other members of the sectors from which we
chose the stocks.
3. Based on the results, we have considered data only from
the Indian stock market. The behaviour of these models may
differ if we consider stocks from other countries. The reason
behind this limitation is due to the emotions associated with
the investors.
4. These indicators may fail to predict any trend if there is
not a considerable amount of fluctuation in the stock market.
This situation happens if all investors are waiting for
limitation is due to the emotions associated with the
investors. 4. These indicators may fail to predict any trend if
there is not a considerable amount of fluctuation in the stock
market. This situation happens if all investors are waiting
for some type of results from that particular company, to
invest.
5. In this paper, we have analyzed static data. In real time
stock market, the prices change every millisecond. Hence,
the decision made at current instant may not be valid at next
instant since the trend has changed due to previous trade.
This problem can be solved only after analyzing the
algorithm with real-time data.[16]
6. In this paper we have relied on data from the year 1994 to
2012 for all stocks which we analyzed. When new data is
fed into the model its accuracy may vary.
F. RISKS
Helps the users in detecting the market trend patterns and
other conditions.
The report contains a number of filter elements
ranging as per the market trends that help the users to
analyze the registered stocks
The report contains a number of shares, their prices, and
Volume Breakouts
It contains stocks that have an unanticipated rise in the
business volume and a rapid rate escalation in terms of cost.
Normally, Stock Chat bots keep stock market at low risk
based on shares the customers/users start, the conversation
which is very common like queries related company rules
and policies, for user related queries. Keeping some of the
confidential conversations in a secure environment is a high
risk feature.
REFERENCES
[1] From Wikipedia, the free encyclopedia: Artificial
Intelligence[Online]. Available:
https://en.wikipedia.org/wiki/Artificial_intelligence
[2] From Wikipedia, the free encyclopedia:
Chatbot[Online]. Available:
https://en.wikipedia.org/wiki/Chatbot
[3] From Wikipedia, the free encyclopedia: Chatbot
Section[Online]. Available:
https://en.wikipedia.org/wiki/Chatbot
[4]parulnith/Building-a-Simple-Chatbot-in-Python-using-
NLTK[Online]. Available:
https://github.com/parulnith/Building-a-Simple-Chatbot-in-
Python-using-NLTK/blob/master/chatbot.txt
[5] Artificial Conversational Entity (ACE)
Wikipedia[Online]. Available:
http://en.wikibedia.ru/wiki/Artificial_Conversational_Entity
_(ACE)
[6] Chatbot - Howling Pixel[Online]. Available:
https://howlingpixel.com/i-en/Chatbot
[7] Chatbot • Wikipedia[Online]. Available:
http://wikipedia.moesalih.com/Chatbot
[8] Stock Market Analysis and Prediction Project[Online].
Available: https://nevonprojects.com/stock-market-analyzer/
[9] Stock Market Analysis And Prediction - Premium
Project Topics and...[Online]. Available:
https://www.writtenproject.com/stock-market-analysis-and-
prediction/
[10] Stock Market Prediction[Online]. Available:
http://ijsrd.com/articles/NCTAAP077.pdf
[11] Ajay Kedia[Online]. Available:
http://www.ajaykedia.com/
[12] Ajay Kedia - Teaching Assistant - University of
Colorado... | LinkedIn[Online]: Available:
https://www.linkedin.com/in/ajay-kedia-01b7015a
[13] Biržos - Portalas investuotojams[Online]. Available:
https://www.traders.lt/list.php?c=l_exch
[14] Project of on Line Trading | Market Maker | Securities
(Finance)[Online]. Available:
https://www.scribd.com/document/14868528/Project-of-on-
Line-Trading
[15] Derivative on India Infoline -Ramesh | Futures Contract
| Derivative...[Online]. Available:
https://www.scribd.com/document/29345293/Derivative-on-
India-Infoline-Ramesh
[16]Loss Prevention in Stock Market[Online]. Available:
https://nevonprojects.com/loss-prevention-in-stock-market/