Anomaly detection and data imputation within time series
Major_Project_Presentaion_B14.pptx
1. DCCR: Deep Collaborative Conjunctive Recommender
for Rating Prediction
Guide
Mrs.T.Aruna Sri
BY(CSEMPBNUM_N11)
SEELAM ROHITH REDDY 2215316447
NANNAMURI SASI KUMAR 2215316432
VAIBHAVI MUTYA 2215316456
REVANTH REDDY K 2215316442
2. ABSTRACT
Collaborative filtering combined with various kinds of deep learning models is appealing to recommender systems,
which have shown a strong positive effect in an accuracy improvement. However, Deep learning model rely heavily
on abundant information to improve prediction accuracy, which has precise data requirements in addition to raw
rating data. Furthermore, most of them ignore the interaction effect between users and items when building the
recommendation model. To address this issues, we propose DCCR, a deep collaborative conjunctive recommender,
for rating prediction tasks that are solely based on the raw ratings. A DCCR is a hybrid architecture that consists of
two different kinds of neural network models (i.e., label encoder, embedded systems and neural networks).We
present a novel recommender model that extracts deep inner features of both users and items that solely depend
on the explicit ratings and extract the interaction features. We describe the details of the structure, input vector,
loss function and training techniques, which are indispensable for the experiments.
We investigate the impacts of the parameters of the proposed model and analyze the relations of these
parameters on the prediction accuracy. An improved activation function Relu for our neural networks are proposed
, which can be specified with input vectors and TensorFlow framework. By conducting considerable experiments on
two datasets, the results show that the proposed model can achieve better accuracy for this particular rating
prediction task. We also discuss the expandability of our model by analysing the depth of neural networks. Several
methods are proposed to adjust the gradient problem of the deep neural networks.
3. Introduction
Recommender System:
Recommender systems are utilized in a variety of areas, and are most commonly recognized as playlist generators for
video and music services like Netflix, YouTube and Spotify, product recommenders for services such as Amazon, or
content recommenders for social media platforms such as Facebook and Twitter.
A recommender system or a recommendation system (sometimes replacing 'system' with a synonym such as platform or
engine) is a subclass of information filtering system that seeks to predict the "rating" or "preference" a user would give to
an item. They are primarily used in commercial applications.
Business Perspective:
4. Methodologies used behind making Recommendations:
Existing System:
Majorly 2 types of filtering methodology is used
1. Content-based recommendation systems: they recommend based on product attributes. Content-based recommendation
systems are recommendation systems that use their knowledge of each product to recommend new products. Let’s say that
you tell a friend that you just watched the movie Iron Man starring Robert Downey, Jr. and that you really liked it. Your friend
might recommend that you watch the movie Avengers next. Both movies are Science fiction film and both movies feature the
same movie star. It could be a good recommendation because the movies have a lot of attributes in common. This is the idea
behind content-based recommendation systems. They try to recommend products that have similar attributes to a product
that the user already liked.
2. Collaborative filtering: they recommend based on similar users Collaborative filtering systems make recommendations only
based on how users rated products in the past, not based on anything about the products themselves. In collaborative filtering,
the recommendation system has no knowledge of the actual product it is recommending. It only knows how other users rated
the product. Collaborative filtering has a very big advantage over content-based recommendations. The advantage is that you
don’t even need to know anything about the products that you’re recommending. As long as you have user review data, you
can build a collaborative filtering recommendation system.
5. • It only works when you already have user reviews to work from. If you don’t have any reviews, you can’t make
recommendations. That means it’s difficult to recommend products to brand new users because new users haven’t
reviewed any products yet. And finally, collaborative filtering tends to favor products with lots of reviews over products
with few or very less reviews. This can make it hard for users to discover new releases since they aren’t likely to get
recommended as often.
• most of them ignore the interaction effect between users and items when building the recommendationmodel.
Limitations
6. • To address these issues, we propose DCCR, a deep collaborative conjunctive recommender, for rating prediction tasks that
are solely based on the raw ratings.
• A DCCR is a hybrid architecture that consists of two different kinds of neural network models.
• To take advantage of the deep learning model in terms of deeper inner feature extraction and fusion, the DCCR is a hybrid
architecture that consists of two different kinds of neural network models (i.e., ES and NN). ES extracts user and item
deeper latent features for the raw ratings data in a separate way, while the main function of an NN is to merge the user
and item feature from the results of the ES at the first layer and extract the higher features (i.e., relationships between user
and item) based on the combined user and item features. Rating prediction of the DCCR model. The input vector is the
feature representation of users and items. The output vector is the predicted ratings..
Proposed System
9. TECHNICAL REQUIREMENTS
• DATASET-for Training Our Model
• Machine Learning Algorithms-for building our model
• Python 3.7 Packages:
• NumPy: for the data handling and operations.
• Pandas: for the data Structure
• H20: for Machine Learning Algorithms, rapidly turning over models
• Matplotlib: for Data Visualization
• Seaborn: for data visualization
HARDWARE REQUIREMENTS
To Run Python a minimum of 4GB Ram is required. Anything Below 4GB would result
in huge differences in results and also Slows down our work. A Minimum Integrated GPU
should be available in the systems that will help understand the visualizations better.
Software Requirements
10. Anaconda-Jupyter Notebooks Directly from the platform and without involving DevOps,data
scientists can develop and deploy AI and machine learning models rapidly into production.
Anaconda provides the tools needed to easily:
IMPLEMENTATION TOOL
11. Tensor flow
Deep learning is a subfield of machine learning that is a set of algorithms that is inspired by the structure and function of the
brain. TensorFlow is the second machine learning framework that Google created and used to design, build, and train deep
learning models. You can use the TensorFlow library do to numerical computations, which in itself doesn’t seem all too
special, but these computations are done with data flow graphs. In these graphs, nodes represent mathematical operations,
while the edges represent the data, which usually are multidimensional data arrays or tensors, that are communicated
between these edges. TensorFlow can hardware, and software requirements can be classified into
FRAMEWORK
12. Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano. It
was developed with a focus on enabling fast experimentation. Being able to go from idea to result with the least possible
delay is key todoing good research. Use Keras if you need a deep learning library that: Allows for easy and fast prototyping
(through user friendliness, modularity, and extensibility).Supports both convolutional networks and recurrent networks, as
well as combinations of the two. Runs seamlessly on CPU and GPU.
Keras
13. Neural Network
Artificial neural networks or connectionist systems are computing systems vaguely inspired by the biological neural networks that
constitute animal brains. Such systems "learn" to perform tasks by considering examples, generally without being programmed
with task-specific rules.
14. Pandas: Pandas is an open-source Python Library providing high-performance data manipulation and analysis tool using its
powerful data structures. The name Pandas is derived from the word Panel Data – an Econometrics from Multidimensional
data. In 2008, developer Wes McKinney started developing pandas when in need of high performance, flexible tool for
analysis of data.
NumPy: NumPy is a Python package. It stands for 'Numerical Python'. It is a library consisting of multidimensional array
objects and a collection of routines for processing of array. Numeric, the ancestor of NumPy, was developed by Jim Hugunin.
Another package Numarray was also developed, having some additional functionalities. In 2005, Travis Oliphant created
NumPy package by incorporating the features of Numarray into Numeric package. There are many contributors to this open
source project.
Seaborn: Seaborn is a library for making statistical graphics in Python. It is built on top of matplotlib and closely integrated
with pandas data structures.
Matplotlib:Matplotlib is a plotting library for the Python programming language and its numerical mathematics extension
NumPy. It provides an object-oriented API for embedding plots into applications using general-purpose GUI toolkits like
Tkinter, wxPython, Qt, or GTK+.
Packages
16. Loading Dataset
We can load the data directly by dragging and dropping the dataset into jupyter notebook homepage. We are using pandas to
load the data. We will also use pandas next to explore the data both with descriptive statistics and data visualization.
34. CONCLUSION
Collaborative filtering has shown to be effective in commercial recommender systems. By combining with neural networks,
CF can represent the latent features of users and items without a manual setting. However, most of related studies use a
single model to perform a rating prediction task without considering the traits of features and ratings. In this model ,we
propose a hybrid neural network model for rating prediction that is named the deep collaborative conjunctive
recommender (DCCR). This model integrates the neural network and label encoder to separately capture the latent
features from users and items and describes the interactions between these features. Numerous factors affect the
prediction performance. Thus, to achieve the optimal model, we evaluate the DCCR with varying factor settings by
considerable contrast experiments. The results show that our DCCR model outperforms other state-of-the-art methods
using two real-world datasets.
35. FUTURE SCOPE
Cosine similarity calculation do not work well when we don't have enough rating for movie or when user's rating for some
movie is exceptionally either high or low.As an improvement on this project some other methods such as adjusted cosine
similarity can be used to compute similarity.
Adjusted cosine similarity, which is similar to cosine similarity, is measured by normalizing the user vectors Ux and Uy and
computing the cosine of the angle between them. However, unlike cosine similarity, when computing the dot product of
the two user vectors, adjusted cosine similarity uses the deviation between each of the user’s item ratings, denoted Ru,
and their average item rating, denoted ¯Ru, in place of the user’s raw item rating. The main advantage of this approach is
that in item-based collaborative filtering, the item vectors consist of ratings from different users who often have varying
rating scales.
36. References
• [1] M. D. Ekstrand, J. T. Riedl, and J. A. Konstan, ``Collaborative ltering
recommender systems,'' Found. Trends Hum.-Comput. Interact., vol. 4,
no. 2, pp. 81173, 2011.
• [2] R. Kumar, B. K. Verma, and S. S. Rastogi, ``Social popularity basedSVDCC recommender system,'' Int. J.
Comput. Appl., vol. 87, no. 14,
pp. 3337, 2014.
• [3] A. Krizhevsky, I. Sutskever, and G. E. Hinton, ``Imagenet classication
with deep convolutional neural networks,'' in Proc. Adv. Neural Inf. Pro-
cess. Syst., 2012, pp. 10971105.
• [4] Y. Jhamb, T. Ebesu, and Y. Fang, ``Attentive contextual denoising autoen-
coder for recommendation,'' in Proc. ACM SIGIR Int. Conf. Theory Inf.
Retr. New York, NY, USA: ACM, 2018, pp. 2734.
• [5] X. Cai, J. Han, and L. Yang, ``Generative adversarial network based het-
erogeneous bibliographic network representation for personalized citation
recommendation,'' in Proc. 32nd AAAI Conf. Artif. Intell., 2018, pp. 18.
• [6] Y. Peng, S.Wang, and B.-L. Lu, ``Marginalized denoising autoencoder via
graph regularization for domain adaptation,'' in Proc. Int. Conf. Neural Inf.
Process. Berlin, Germany: Springer, 2013, pp. 156163.
• [7] P. Baldi and P. J. Sadowski, ``Understanding dropout,'' in Proc. Adv. Neural
Inf. Process. Syst., 2013, pp. 19.
