The goal of a recommender
system is to generate meaningful recommendations to
a collection of users for items or products that might
interest them.
Many of the largest e-commerce websites are already
using recommender systems to help their customers
find products to purchase or download.
2. INTRODUCTION
Users are usually looking for items
they find interesting
Website is a collection of these items
Huge amounts of data available
We propose a system using a
combination of conventional
techniques and genetic algorithm
Used by E.commerce site
3. AIMS AND OBJECTIVES
Generate
Prompt
meaningful recommendations
responses and adaptation to changing
preferences
High
recommendation accuracy
Enriched
user interface
4. WHAT IS RECOMMENDATION SYSTEM
Internet-based software tools
Provides user with intelligent suggestions
Recommender systems for music data produce a list of
recommendations
Content-based filtering
Collaborative filtering
6. PLAN OF ACTION (Item profile+User
profile+Prediction mechanism
Item profile
likes
recommend items with
similar content
build
recommend
Good Life
E.T
Run This Town
Gold Digger
match
Hip-hop
Kanye west
Rihanna…
User profile
7. COLLABORATIVE FILTERING
Predict items based on the items previously rated by other
similar users
Recommended items that are preferred by other people
Example of a collaborative filtering technique.
9. LITERATURE SURVEYED
Existing Systems
Proposed system
Focus on accessed items only
Considers all items available in
database
Not prompt to immediate
changes in user interest
IGA prompts to immediate
changes in user preferences
Unable to learn from user
actions and implement them
Adapts to user actions to compute
accordingly
Accuracy is not great
The offspring generated are quite
optimal
10. GENERIC RS
For a typical recommender system, there are three
steps
1.
User provides some form of input to the
system.
2.
These inputs are brought together to form a
representation of the users likes and dislikes.
3.
System computes recommendations
11. GENETIC ALGORITHM
A genetic algorithm (GA) is a search heuristic that mimics the
process of natural evolution
Genetic algorithms belong to the larger class of evolutionary
algorithms (EA), which generate solutions to optimization
problems
Use techniques inspired by natural evolution, such as
replication, inheritance, mutation, selection, and crossover
12. GENETIC ALGORITHM PROCEDURE
1.
Choose the initial population of individuals
2.
Valuate the fitness of each individual
3.
Repeat until termination
4.
Select the best-fit individuals for reproduction
5.
Breed new individuals through crossover and mutation
6.
Evaluate the individual fitness of new individuals
7.
Replace least-fit population with new individuals
14. SYSTEM ANALYSIS
The proposed system is divided into three phases, namely,
1.
Music Feature Extraction
2.
Evaluation
3.
Interactive Genetic Algorithm
In our proposed system, IGA works in three steps:
Selection,Crossover, and Matching.
19. SCOPE OF THE SYSTEM
More than half the music now-a-days is downloaded
The trend is bound to rise exponentially
Virtually impossible to go through the heap of data and
choose
Recommendations from primary sources are too narrow
They amount to a bulk of online sales across sectors
These systems are attracting huge attention and
investments from e-commerce sites
21. CONCLUSION
We propose a real-time genetic
recommendation method for music data in
order to overcome the shortfalls of existing
recommendation systems based on content based
filtering and other such techniques that fail in
reflecting in the current user preferences.
22. REFERENCES
[1] Hyun – Tae Kim, Eungyeong Kim, “Recommender
system based on genetic algorithm for music data”, 2nd
International Conference on Computer Engineering and
Technology, 2010.
[2] J. Ben Schafer, Joseph Konstan, John Riedl,
“Recommender Systems in ECommerce”,2007.
[3]Sachin Bojewar and Jaya Fulekar , “Application of
Genetic Algorithm For Audio Search with Recommender
System”, 2006.
[4] Tom V. Mathew, “Genetic algorithm”,2005.
Editor's Notes
We proposed a new recommender system for music data by combining the content based filtering technique with interactive genetic algorithmthe content based approach has some limitation such tha it focuses on only the accessed items and is not prompt to immediate changes in the potential interest of users.to overcome these limitations,we combine the content based filtering approach and genetic algorithm in our prposedsystGAs produces offspring(i.e;new solutions) by the combination of selected solutionswe proposed real-time genetic recommendation method in order to overcome the existing recommendation techniques are notreflect the current user`s intend. With the genetic algorithm newer solutions can be generatedproviding optimal solution each time when the algorithm is made to run, thus providingmutations. This method can be compared with the existing ones which lack the quality of providing accurate results.
For a typical recommender system, there are three stepsThe user provides some form of input to the system. These inputs can be both explicit and implicit . Ratings submitted by users are among explicit inputs whereas the URLs visited by a user and time spent reading a web site are among possible implicit inputs.These inputs are brought together to form a representation of the users likes and dislikes. This representation could be as simple as a matrix of items-ratings, or as complex as a data structure combining both content and rating information.The system computes recommendations using these user profiles.
WORKING:Apply genetic algorithm to music recommendation system. The system can detect and recommend appropriate songs which are suitable for user’s musical preference. And, the system requires pre-processing which is feature (i,e. tempo, chord, pitch, etc.) extraction from music. It based on shuffle operation. (i.e, play song randomly) At first time, the system recommends songs randomly and user cans judge’s song’s preference by controlling their devices or program. Just click the next song button.
Description: This is the general list where all thesongs of different category is listed. The user canlisten to songs as well as rate them. Once userprovides ratings, user is directed to the recommendedlist of songs based on user preference
Description: This is the final output page of therecommender system. This page displays the top tenrecommendations to the user based o his preferences.