Scribd
Upload
11 views13 pages

Moradabad Institute of Technology

This is recommendation project presentation.

Uploaded by

azimfarazch3
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
11 views13 pages

Moradabad Institute of Technology

This is recommendation project presentation.

Uploaded by

azimfarazch3
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 13

MORADABAD INSTITUTE OF TECHNOLOGY

A Presentation on Collaborative Filtering user


and Item Based Movie or Product
Recommendation System
PRESENTED BY-

SHIVANSHU AGARWAL

VISHAL SAINI
UDIT
SAURABH SAINI
UMANG MATHUR
RECOMMENDER SYSTEM
• Subclass of information filtering system that
seek to predict the rating or prefence that a
user would give to an item

Helps deciding in what to wear what to buy


what stocks to purchase etc

Applied ina variety of application like movies


books, research arcticles
EVOLUTION
• People relied on the recommendations from
their peers
• This method doesnt take the personal
preference of the user in to account
• It also limits the search space

• Computer based recommendation system


overcomes this by expanding the search space
and providing a more fine tune results
TASK OF RECOMMENDATION SYSTEM
• Predict task- The user Preference for an item

• Recommend Task- Produce best ranked list of


n items for users need
COLLABORATIVE FILTERING
• Collaborative filtering is the process of
filtering for information or patterns using
techniques involving collaborative among
multiple agents viewpoints data sources etc
USER-USER COLLABORATIVE FILTERING
• Basic idea- find other users whose past rating
behaviour is similiar to that of the current user
and use their rating on other items to predict
what the current user will like
• Required rating matrix and similarity function
that computers the similarity between two
users
ITEM-ITEM COLLABORATIVE FILTERING
• Basic idea-Recommend items that are similiar
to the users highly preffered items

• Provides performance gains by lending itself


well to pre computing similarity
EVALUATING RECOMMENDER SYSTEMS
• It can be costly to try algorithm on real sets of
users and measure the effects
• Offline algorithm evaluations
• pre test algorithm in order to understand
user testing
• It is beneficial for performing direct objectives
• Comparison of different algorithm in a
reproducible fashion
ONLINE EVALUATION
• Offline evaluation through useful is limited to
operating on past data
• Recommender system with similiar metric
performance can still give different results and
a decrease in the error may or may not make
the system better at meeting the user needs
• For this online user testing is needed
COLD START PROBLEM
• Problem of providing recommendations when
there is not yet data available
• Item cold start –A new item has been added
to the database
• User cold start- A new user has joined the
systems but their preference are not yet
known
RATING SCALES
• Group lens used a 5 star scale
• Jester uses a semi continuous -10to -10
graphical scale
• Ringo used a 7 star scale
• Pandora music uses a like/dislike method
DEALING WITH NOISE
• Noise in rating can be introduced by –normal human error
and other factors

• Natural noise in rating can be detected by asking users to


re rate items

• Another approach is detecting and ignoring noisy data by


comparing each rating to the user predicted preference for
that item and discarding rating whose difference exceed
some threshold from the prediction and recommendation
process
• THANKU

You might also like