Você está na página 1de 5

CMPE 491 Senior Project I

Project Specifications Report


By
Cihad Tekinbaş
Enes Arslan
Berke Evrensevdi

Supervisor:
Tayfun KÜÇÜKYILMAZ

Jury Members:
Aslı GENÇTAV
Orkunt SABUNCU
Contents
1. Introduction .......................................................................................................................................... 3
2. Description ............................................................................................................................................ 3
3.Constraints ................................................................................................................................................. 3
3.1. Implementation Constraint................................................................................................................ 3
3.2.Communication Constraint ................................................................................................................. 3
3.3.Language Constraint ........................................................................................................................... 4
3.4.Ethical Constraint ................................................................................................................................ 4
3.4.1.Professional and Ethical Conduct ................................................................................................ 4
4.Requirements............................................................................................................................................. 4
4.1.Functional Requirements .................................................................................................................... 4
4.2.Non-functional Requirement .............................................................................................................. 5
5.References ................................................................................................................................................. 5

2
1. Introduction

Time is one of the most important things for the people, especially today. People started
to live faster compared to old times. So, everyone wants to use his/her time efficiently. That
is how the recommender systems were born. Recommender systems were first mentioned
in a technical report as a "digital bookshelf" in 1990 by Jussi Karlgreen at Columbia
University [1]. Since then so many research has done. However, it does not mean it is
enough. To give an example, in 2016, there were 736 films released in US cinemas; twice
the number in 2000 [2]. In other words, the number of the movies released each year has
increased massively in the world. So, people need to be recommended to save their time.
Our aim is to improve the already existing recommender systems in order to increase the
accuracy of earlier research.

2. Description
“Movie Predictor” project can be described as enhanced recommender system. As it
was mentioned earlier, the user reviews, ratings and information about movies will be used
together to improve the recommender system. Our intention is to use the system on IMDB-
like websites to perform and observe the results. IMDB recommendation system will be
replaced by ours after the system is done. Thanks to the system people do not need to
waste their time to choose a movie that they might like after they read tons of reviews.
Instead the recommendation system will suggest appropriate movies.
We have done research about the dataset we will use in our project and found Amazon
and IMDB movie and review datasets. In the case the data is too noisy to train the model,
we have an alternative plan which is to use an API providing us to retreat the necessary data
from IMDB.

3.Constraints
3.1. Implementation Constraint
• Proper datasets are needed to train our model.
• The website will have a Python server.
• It will be a web application
• Open source libraries will be used for the development.
• MATLAB will be used to edit the data.

3.2. Communication Constraint


• GitHub will be used to communicate with other group members and assign tasks.

3
3.3. Language Constraint
• The data and website will be in English so the system cannot be used in any
Turkish website.

3.4. Ethical Constraint


• Public data will be used to predict more accurate movies for the person.
• Customer needs to give his/her consent when s/he registers to the website in
the user agreement document.
• The private data of the users will not be used.

3.4.1. Professional and Ethical Conduct


During all the stages of the progress in the project we all team members have agreed to
follow Professional and Ethical Conducts listed below.

• Contribute to society and to human well-being, acknowledging that all people are
stakeholders in computing. [3]
• avoid injuring others, their property, reputation, or employment by false or
malicious action. [4]
• Be fair and take action not to discriminate [5]
• To assist colleagues and co-workers in their professional development and to
support them in following this code of ethics [6]
• To respect the privacy of the people and the data they share.

4.Requirements

The requirements are categorized in two groups; functional and non-functional


requirements. The requirements mentioned below may be changed over time because of the
fact that we are at the very early stage in the project.

4.1. Functional Requirements


• The server application shall receive and handle requests for recommendations
• The system shall take feedback from the users whether they like the
recommendations.
• The system should encrypt data of users.

4
• The information about the user’s preference shall be updated time to time.

4.2. Non-functional Requirement


• The response time of the website should be one second.
• The system should not shut down itself when it is used.
• The website should produce accurate recommendations that is appropriate for the
user.
• The server should be capable of giving response to more than 100 people at the
same time.

5. References
[1]"Recommender system", En.wikipedia.org, 2019. [Online]. Available:
https://en.wikipedia.org/wiki/Recommender_system. [Accessed: 11- Oct- 2019].
[2]"How many films are released each year?", Stephen Follows, 2019. [Online]. Available:
https://stephenfollows.com/how-many-films-are-released-each-year/. [Accessed: 11- Oct-
2019].
[3] [5]"The Code affirms an obligation of computing professionals to use their skills for the
benefit of society.", Acm.org, 2019. [Online]. Available: https://www.acm.org/code-of-ethics.
[Accessed: 11- Oct- 2019].
[4] [6] "IEEE Code of Ethics", Ieee.org, 2019. [Online]. Available:
https://www.ieee.org/about/corporate/governance/p7-8.html. [Accessed: 11- Oct- 2019].

Você também pode gostar