NETFLIX DATA ANALYTICS

i
BONAFIDE CERTIFICATE

ii
ACKNOWLEDGEMENT

iii
 ABSTRACT

In the context of such an era where nearly everything is based on big data,
personalized recommendation systems are becoming increasingly valuable for
research. Machine learning has attained great achievements in numerous fields
by virtue of its powerful computing power and extraordinary nonlinear
transformation capabilities. Applying machine learning to a recommendation
system that needs to mine and extract features from massive amounts of data
will not only help the development of recommendation algorithms, but also
improve the algorithm performance and thus improve the user experience. This
project introduces a recommendation algorithm based on LSTM-CNN and
applies it to the recommendation of movies by mining user behavior data and
recommending movies with higher ratings to them. This article uses the data
provided by the movie website MovieLens. It is testing set and training set that
the data is divided into, and Top-N recommendation list is produced for the
training set, while the algorithm is evaluated on the testing set. It is the features
of the data that LSTM-CNN can effectively extract and complete the
recommendation from the results

CHAPTER TITLE NAME PAGE

iv
NO

NO

ABSTRACT iv

LIST OF FIGURES viii

LIST OF ABBREVATIONS ix

1. INTRODUCTION 1

1. BACKGROUND 1
1
3
1. MOTIVATION
3
2
3
1. OBJECTIVE
3 4

1. SCOPE OF THE PROJECT

4
ORGANIZATION OF THE REPORT
1.
5

2 LITERATURE SURVEY 5

2.1 INFERENCE OF THE LITERATURE REVIEW 9

3 SYSTEM ANALYSIS 10

3.1 PROBLEM DEFINITION 10

3.2 PROPOSED SYSTEM 10

v
 3.3 ADVANTAGES 11

3.4 SYSTEM SPECIFICATION 11

4 SYSTEM ARCHITECTURE 12

4.1 OVERALL ARCHITECTURE 12

4.2 MODULE DESCRIPTION 12

4.3.1 DATA SET DESCRIPTION 13

4.3.2 DATA PRE-PROCESSING 16

4.3.3 MODEL BUILDING 17

4.3.4 TRAIN THE MODEL 18

4.3.5 TEST MODEL 18

5 SYSTEM IMPLEMENTATION 20

5.1 HARDWARE AND SOFTWARE USED 20

5.3.1 INTRODUCTION TO PYTHON 20

5.3.2 TENSORFLOW FRAMEWORK 27

5.3.3 MACHINE LEARNING 27

5.3.4 ANALYSIS 28

5.4 CODE IMPLEMENTATION 32

6 RESULT AND DISCUSSION 33

7 CONCLUSION 37

vi
 LIST OF FIGURES

FIGURE TITLE PAGE NO.

NO.

4.1 PROPOSED ARCHITECTURE. 12

4.2 CONVOLUTION NERUAL NETWORK 15

6.1 MOVIE RECOMMENDATATION SCREEN 34

SHOT 1

6.2 MOVIE RECOMMENDATATION SCREEN 35

SHOT 2

6.3 MOVIE RECOMMENDATATION SCREEN 35

SHOT 3

vii
 LIST OF ABBREVATIONS

S.NO ACRONYMS

1 GRU Gate Recurrent Unit

2 JSON JavaScript Object Notation

3 LSTM Long Short Term Memory

4 PCA Principle Component Analysis

5 MTCNN Multi-Task Cascaded Convolutions Neural

Networks

6 ANN Artificial Neural Network

7 CNN Convolution Neural Network

8 SVM Support Vector Machine

9 PyPI Python Package Index

10 MAPE Mean absolute percentage error

11 RMSE Root Mean Square Error

viii
ix