MALLA REDDY INSTITUTE OF TECHNOLOGY (RJ)
Maisamaguda, Dhulapally (Post Via Hakimpet), Secunderabad -10.
A TECHNICAL SEMINAR
PRESENTATION
ON
“TITLE NAME”
UNDER THE GUIDANCE BY
GUIDE NAME
Made By
Student Name
Roll number
CONTENTS
• Abstract
• Problem Definition
• Existing System and Disadvantages
• Proposed System and Advantages
• Recommended System Methodologies
• System Requirements
• Architecture Diagram
• Modules
• Results
• Conclusion
• Future Enhancements
ABSTRACT
o Providing a useful suggestion of products to online users to increase their
consumption on websites is the goal of many companies nowadays.
o In order to do all these tasks automatically, a recommender system must be
implemented.
o In this paper, a movie recommendation mechanism within Netflix will be built.
The dataset that was used here consists of over 17K movies and 500K+
customers.
o The main types of recommender algorithm are Popularity, Collaborative
Filtering, Content-based Filtering and Hybrid Approaches.
PROBLEM DEFINITION
• A movie recommendation is important in our social life due to its strength in
providing enhanced entertainment. Such a system can suggest a set of
movies to users based on their interest, or the popularities of the movies.
• Although, a set of movie recommendation systems have been proposed,
most of these either cannot recommend a movie to the existing users
efficiently or to a new user by any means.
EXISTING SYSTEM
 We propose a movie recommendation system that has the ability to
recommend movies to a new user as well as the others.
 It mines movie databases to collect all the important information, such as,
popularity and attractiveness, required for recommendation.
 It generates movie swarms not only convenient for movie producer to plan
a new movie but also useful for movie recommendation.
DISADVANTAGES
• Numerical measure of how different are two data objects
– Lower when objects are more alike
– Minimum dissimilarity is often 0
– Upper limit varies
1. Does not work well with large dataset
2. Does not work well with high dimensions
PROPOSED SYSTEM
• We propose below methodology for solving the problem. Raw data collected
would be pre-processed for missing data, anomalies and outliers. Then an
algorithm would be trained on this data to create a model. This model would
be used for forecasting the final results.
• ETL stands for Extract, Transform and load. It is a tool which is a
combination of three functions. It is used to get data from one database and
transform it into a suitable format.
• Data preprocessing is a data mining technique used to transform sample
raw data into an understandable format. Real world collected data may be
inconsistent, incomplete or contains an error and hence data preprocessing
is required.
ADVANTAGES
• More accurate results
• It is robust
• It is efficient
HARDWARE REQUIREMENTS
•System. : Intell I-3, 5, 7 Processor.
•Hard Disk. : 500 GB.
•Floppy Drive. : 1.44 Mb.
•Monitor. : 14’ Colour Monitor.
•Mouse : Optical Mouse.
•RAM : 2Gb.
SOFTWARE REQUIREMENTS
• Operating system : Windows 7,8,10 Ultimate, Linux, Mac.
• Front-End. : Python.
• Coding Language. : Python.
• Software Environment : Anaconda(jupyter or spyder).
ARCHITECTURE DIAGRAM
MODULES
• NumPy. : Base n-dimensional array package
• SciPy. : Fundamental library for scientific computing
• Matplotlib. : Comprehensive 2D/3D plotting
• IPython. : Enhanced interactive console
• Sympy. : Symbolic mathematic
• Pandas. : Data structures and analysis
RESULTS
CONCLUSION
• In this presentation, we first address the importance of movie
recommendation system .
• Recommendations in line with these interests are a lot more intricate to
generate than simpler generic recommendations.
• It solves the new item recommendation problem and provides an idea about
the current trends of the popular movies and user interests.
• We also proposed algorithm for mining interesting and popular movie
genres to recommend movies to a new user.
• This is very helpful for movie producer to plan new movies.
FUTURE ENHANCEMENT
• The user interface through the website can be made easier to access
through user profiling. The user’s previous like, dislikes etc. can be stored.
• This can also be developed as a standalone application (engine) which can
be used by small e-commerce site vendors to acquire and attach to their
sites.
• Sentiment analysis can also be applied to “comments” information to
identify the emotion behind the comments (positive, negative or neutral) to
recommend movies appropriately.
THANK YOU!

IV YEAR TECHNICAL SEMINAR PRESENTATION.pdf

  • 1.
    MALLA REDDY INSTITUTEOF TECHNOLOGY (RJ) Maisamaguda, Dhulapally (Post Via Hakimpet), Secunderabad -10. A TECHNICAL SEMINAR PRESENTATION ON “TITLE NAME” UNDER THE GUIDANCE BY GUIDE NAME Made By Student Name Roll number
  • 2.
    CONTENTS • Abstract • ProblemDefinition • Existing System and Disadvantages • Proposed System and Advantages • Recommended System Methodologies • System Requirements • Architecture Diagram • Modules • Results • Conclusion • Future Enhancements
  • 3.
    ABSTRACT o Providing auseful suggestion of products to online users to increase their consumption on websites is the goal of many companies nowadays. o In order to do all these tasks automatically, a recommender system must be implemented. o In this paper, a movie recommendation mechanism within Netflix will be built. The dataset that was used here consists of over 17K movies and 500K+ customers. o The main types of recommender algorithm are Popularity, Collaborative Filtering, Content-based Filtering and Hybrid Approaches.
  • 4.
    PROBLEM DEFINITION • Amovie recommendation is important in our social life due to its strength in providing enhanced entertainment. Such a system can suggest a set of movies to users based on their interest, or the popularities of the movies. • Although, a set of movie recommendation systems have been proposed, most of these either cannot recommend a movie to the existing users efficiently or to a new user by any means.
  • 5.
    EXISTING SYSTEM  Wepropose a movie recommendation system that has the ability to recommend movies to a new user as well as the others.  It mines movie databases to collect all the important information, such as, popularity and attractiveness, required for recommendation.  It generates movie swarms not only convenient for movie producer to plan a new movie but also useful for movie recommendation.
  • 6.
    DISADVANTAGES • Numerical measureof how different are two data objects – Lower when objects are more alike – Minimum dissimilarity is often 0 – Upper limit varies 1. Does not work well with large dataset 2. Does not work well with high dimensions
  • 7.
    PROPOSED SYSTEM • Wepropose below methodology for solving the problem. Raw data collected would be pre-processed for missing data, anomalies and outliers. Then an algorithm would be trained on this data to create a model. This model would be used for forecasting the final results. • ETL stands for Extract, Transform and load. It is a tool which is a combination of three functions. It is used to get data from one database and transform it into a suitable format. • Data preprocessing is a data mining technique used to transform sample raw data into an understandable format. Real world collected data may be inconsistent, incomplete or contains an error and hence data preprocessing is required.
  • 8.
    ADVANTAGES • More accurateresults • It is robust • It is efficient
  • 9.
    HARDWARE REQUIREMENTS •System. :Intell I-3, 5, 7 Processor. •Hard Disk. : 500 GB. •Floppy Drive. : 1.44 Mb. •Monitor. : 14’ Colour Monitor. •Mouse : Optical Mouse. •RAM : 2Gb.
  • 10.
    SOFTWARE REQUIREMENTS • Operatingsystem : Windows 7,8,10 Ultimate, Linux, Mac. • Front-End. : Python. • Coding Language. : Python. • Software Environment : Anaconda(jupyter or spyder).
  • 11.
  • 12.
    MODULES • NumPy. :Base n-dimensional array package • SciPy. : Fundamental library for scientific computing • Matplotlib. : Comprehensive 2D/3D plotting • IPython. : Enhanced interactive console • Sympy. : Symbolic mathematic • Pandas. : Data structures and analysis
  • 13.
  • 14.
    CONCLUSION • In thispresentation, we first address the importance of movie recommendation system . • Recommendations in line with these interests are a lot more intricate to generate than simpler generic recommendations. • It solves the new item recommendation problem and provides an idea about the current trends of the popular movies and user interests. • We also proposed algorithm for mining interesting and popular movie genres to recommend movies to a new user. • This is very helpful for movie producer to plan new movies.
  • 15.
    FUTURE ENHANCEMENT • Theuser interface through the website can be made easier to access through user profiling. The user’s previous like, dislikes etc. can be stored. • This can also be developed as a standalone application (engine) which can be used by small e-commerce site vendors to acquire and attach to their sites. • Sentiment analysis can also be applied to “comments” information to identify the emotion behind the comments (positive, negative or neutral) to recommend movies appropriately.
  • 16.