A Role of Machine Learning Algorithms for Demand Based Netflix

Recommendation System

Tejaswini Bhoye

, Aishwarya Mane

, Vandana Navale

, Sangeeta Mohapatra

Sandeep Chitalkar

, Vishal Borate

5 a

and Yogesh Mali

6 b

Department of Computer Engineering, Marathwada Mitramandal Institute of Technology, Lohegaon, Pune, India

Department of Computer Engineering, Marathwada Mitramandal College of Engineering, Pune, India

Department of Computer Engineering, Ajeenkya DY Patil School of Engineering, Lohegaon, Pune, India

Department of Artificial Intelligence and Data Science, Dr. D.Y Patil Institute of Technology, Pimpri, Pune, India

Department of Computer Engineering, Dr. D. Y. Patil College of Engineering and Innovation, Talegaon, Pune, India

School of Engineering, Ajeenkya DY Patil University Lohegaon, Pune, India

Keywords: Machine Learning, Collaborative Filtering, Content-based Filtering, SVD, Personalization, User Engagement,

Streaming Platforms.

Abstract: The rise of streaming services, personalized content recommendation is one of the critical features enhancing

user engagement and retention. This paper presents a comprehensive analysis of the Netflix recommendation

system, which bases its predictions on machine learning and collaborative filtering from behavioural data

about the viewers’ preferences. It combines the two techniques into a hybrid approach to create personalized

recommendations. It further honed the system using the technique of Singular Value Decomposition with

enhanced accuracy for recommendations relevant to the viewer. This is realized by dynamism whereby it is

possible to learn through the models that the viewers’ tastes change over time by feature engineering and

techniques based on deep learning. Hence, there is alignment with actual viewer preferences at the more

precise level. This research demonstrates and depicts how these methodologies efficiently work toward

improving viewer satisfaction, and therefore significantly contribute towards the competitive advantage of a

company such as Netflix, within the very competitive streaming market. The study provides prime ideas and

guidelines for progress into future advancement regarding the recommendation system in streaming platforms.

1 INTRODUCTION

In the streaming industry, one change in user

experience due to machine learning is the Netflix

recommendation system. This uses content-based

filtering, collaborative filtering, and hybrid models to

make recommendations tailored from large datasets

of viewing tastes and habits. Recent research through

deep learning algorithms helps in discovering

complex usage patterns, and hence adaptation

algorithms need to be continually updated based on

the analysis for enhancing users’ engagement and

reducing attrition. In paper (More, Jadhav, et al.,

2024) author proposed a hybrid model integrating the

improved CBF and CF using CNNs. They also

introduced Cascade Hybrid Filtering, which

outperformed all baselines with an RMSE of 0.6325.

https://orcid.org/0009-0009-7585-6667

https://orcid.org/0009-0004-0582-9595

Additional work in optimizing CNN feature

extraction would support nuanced recommendations.

In paper (Mali, Pawar, et al., 2023) authors combined

CF with K- means clustering to reduce the

computational cost of CF on large datasets, with

RMSEs of 0.6354. It is a good example of how

clustering may improve the precision of

recommendations.

In paper (Mali, Mohanpurkar, et al., 2015)

according to authors, the recommendation system of

Netflix shapes user preferences through “taste

communities” because it creates algorithmic taste-

making. The authors of this paper focus on the

cultural implications of tailoring content

recommendations (Nalawade, Pattnaik, et al., 2004),

for recommending content, Sharma et al. applied

feature extraction from metadata; they also noted the

212

Bhoye, T., Mane, A., Navale, V., Mohapatra, S., Chitalkar, S., Borate, V. and Mali, Y.

A Role of Machine Learning Algorithms for Demand Based Netﬂix Recommendation System.

DOI: 10.5220/0013589500004664

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 3rd International Conference on Futuristic Technology (INCOFT 2025) - Volume 2, pages 212-220

ISBN: 978-989-758-763-4

importance of data visualization in raising user

engagement (Patil, Zurange, et al., 2024). To deal

with the data sparsity problem, in paper (Modi, Modi,

et al., 2024) authors devised a co-clustering algorithm

that proved to have accuracy gain of 7.91% as

compared to classical CF.

In handling the missing data modalities, Agrawal

et al. proposed a meta-learning approach which

utilizes a Graph Attention Network. This resulted in

greatly reducing the RMSE of multi-modal

recommendation systems. In paper (Mehta,

Chougule, et al., 2024) the methodology used

significantly improved Movie Lens datasets that

address the temporal aspect for dynamic user

preferences on the matrix factorization model

(Shimpi, Balinge, et al., 2024). The Figure 1. Shows

the Flowchart of recommendation system.

Figure 1: Flow Diagram for Recommendation System.

In paper (Ingale, Wankar, et al., 2024) authors

have combined data for Netflix and Amazon Prime

using the analytics of big data and the enhancement

in terms of cross-platform movie recommendations

are done on the grounds of providing platform-

specific suggestions. The flowchart illustrates how a

recommendation system is built by the process. A set

of dataset and exploratory data analysis determine the

trend and abnormality in data. Feature extraction

selects those important features to model the data.

Data cleaning manages missing values, and it uses

one-hot encoding on categorical data before

processing. Before training the model for trend,

validation is performed for the processed data. The

hybrid model uses a variety of recommendation

strategies

high

accuracy

level.

delivers

recommendations through the trained model to the

users.

1.1

Singular Value Decomposition

(SVD)

From Figure 2 SVD is one of the major benefits is the

simplification of some data that help in improving the

prediction accuracy, especially reducing the number

of features of the complex information that Netflix

collects. Of course, such information usually

includes, but is not restricted to, user interactions,

preferences, and content attributes. SVD makes it

possible to support personalized recommendations

that are more closely related to the interests of each

individual user by identifying latent factors that stand

in for the hidden user interests and content features.

SVD also addresses the sparse data problem faced

by Netflix, which basically means that most of the

viewers haven’t engaged with most of the content

items available. Even for less active users, SVD

guarantees strong recommendations by precisely

predicting missing elements of the user-content

matrix. This is possible because of the computational

efficiency of SVD, enabling it to process very large

volumes of data from Netflix’s at just about virtually

no computation cost, which also relates to an

important requirement for real-time dynamic

suggestions.

SVD Architecture is represented as in the Figure 2.

Figure 2: SVD Architecture.

2 RELATED WORK

In paper (More, Jadhav, et al., 2024) authors have

suggested a hybrid approach using CNN that

combines Collaborative Filtering (CF) with an

improvement in Content- Based Filtering (CBF) to

enhance the hybrid recommendations. In their

“Cascade Hybrid Filtering” approach, the user-item

interactions enable the first stage to continue through

CF that begins recommending some movies based on

those interactions, then continue the refinement by

A Role of Machine Learning Algorithms for Demand Based Netﬂix Recommendation System

213

assessing how much those movies resemble,

according to the contents in CBF. The performance of

the approach was tested on MAE and RMSE metrics

and it gave RMSE 0.6325 with an accuracy of 6 per

over the baseline models.

In paper (Mali, Pawar, et al., 2023) authors

proposed a Netflix recommendation system based on

the combination of Collaborative Filtering and K-

means clustering. Although CF is the most popular

technique, the high computational cost in case of

large datasets makes this algorithm inefficient.

Therefore, authors used K-means clustering for

grouping users with common interests before

applying CF. They used Twitter data mainly to obtain

user ratings; ratings were converted using Text Blob

polarity scores. This combined model achieved the

lower RMSE of 0.6354 in comparison to the

individual CF methods.

In paper (Mali, Mohanpurkar, et al., 2015) authors

have given recommendations on Netflix by

overcoming the cold- start problem in a hybrid

recommendation model based on the combination of

Collaborative Filtering and Content-Based Filtering.

Their system is making use of machine learning

algorithms to compute user behaviour and content

attributes, thereby bringing about a delicate balance

between item-based and user-based

recommendations.

In paper (Nalawade, Pattnaik, et al., 2004)

auuthors analyses NRS, one of its parts includes

critical questioning as to how it serves to central

purpose constructing preferences in the vast range of

users through “algorithmic taste-making”. In

application of a reverse engineering of NRS, Pajkovic

reveals how both methods of content-based filtering

along with collaborative filtering amalgamate by

putting users together to produce a form of ”taste

communities,” which, while spreading out beyond

national borders, stay coherent.

3 PROPOSED METHDOLOGY

3.1

Data Collection

The dataset utilized in this research was sourced from

kaggle Netflix Recommendation System. The

primary datasets include:

User Features

User ID: Every user is assigned a unique number, for

example, user001.Age: The age of the user can be

used while making the demographic analysis.

Gender: It can include the gender of the user

while making the suggestions.

Material: It depends on the subscription model.

3.1.1

Features of the Content

Movie/Show ID: A unique number assigned to every

title.

Title: The title of the film or the show. Genres are

classifications that apply to the plot of a movie or the

television show; among these are action, comedy,

drama, science fiction, and many more (Mulani,

Nandgaonkar, et al., 2024).

Description: It should be clear whether a user would

want to read the information based on a brief

overview or description of it (Sonawane, Mulani, et

al., 2024).

Release Year: It gives the year that this content was

released, which can therefore make one have a better

idea of how old or new the content is (Mandale, Modi,

et al., 2024).

Language: The main language used within the

content is this one, which is information that may be

a decision maker when determining what to watch

(Sengupta, Nalawade, et al., 2024), (More, Khane, et

al., 2024).

Cast: The females and actors who feature in the

movie or TV program. Information about the actors

in the movie help describe a user’s preferences

(Wanaskar, Dangore, et al., 2024).

Director: Information about who directed the movie

may affect whether or not to view it (More, Ramishte,

et al., 2024).

Production Company: Company that produced the

above stated film (Palkar, Jain, et al., 2024),

(Dangore, Modi, et al., 2024).

3.1.2

User-to-User Communication

User Evaluation Features Rating at specific instance

such as 1 to 5 stars and likes/dislike. This defines the

list of movies or a series a viewer has seen, and this

list for a viewer is termed the watch list (Dangore,

Bhaturkar, et al., 2024), (More, Shinde, et al., 2024).

Viewing time: The number of hours, say 90 minutes,

that a person spends viewing material (Vaidya,

Dangore, et al., 2024).

Watchlist: Titles that a user has added to their

watchlist but hasn’t watched (Sawardekar, Mulla, et

al., 2025).

3.2

Data Pre-Processing

3.2.1

Data Cleaning & Missing Values

Netflix deals with the missing data about the user

INCOFT 2025 - International Conference on Futuristic Technology

214

Such as missing ratings for any content by imputation

techniques or rejection of incomplete records (Modi,

Mali, et al., 2024), (Bhongade, Dargad, et al., 2024).

3.2.2

Similarity Computation

The system identifies users similar to the target user.

This is done by comparing their movie preferences or

other data points (Mali, Yogesh., et al., 2023).

3.2.3

Prediction

A machine learning model uses the similarity

information to make predictions about what movies

the target user would likely enjoy (Kale, Hrushikesh,

et al., 2024).

3.2.4

Recommendations

The model generates a list of recommended movies

for the target user, based on the predictions made

(Inamdar, Faizan, et al., 2024).

3.2.5

Normalization

The ratings obtained from the users may be

normalized, such that it will be consistency in

smoothness (Jagdale, Sudarshan, et al., 2020), (Modi,

Mali, et al., 2024).

3.2.6

Data Transformation

Encoding User and item features: Netflix assigns

numeric representations both to the users and content.

The information regarding both user and item is

encoded in a way so that all the categorical features

like user demographics, genres of movies, among

others convert into numerical vectors using

techniques such as one-hot encoding (Mali, Sharma,

et al., 2023).

Dimensionality Reduction: high dimensionality of

the data is reduced using for example a technique like

SVD or PCA(Modi, 2024). For instance, reducing

ratings over thousands of movies to identify key the

latent factor is the preference of users. The pre-

processing steps are shown in Figure 3.

Figure 3: Flow diagram of Pre-processing data.

3.3

Encoding Categorical Variables

For ease of modelling, categorical variables within

Netflix dataset have been label-encoded into numeric

formats. The process of label encoding assigns a

unique integer to each category so that machine

learning algorithms can handle it easily. The

categorical variables genre, content rating and

subscription tier were encoded to differentiate the

categories of different types of contents and levels of

subscription made by users (Mali, and, Chapte, 2014).

3.4

Train-Test Split

To test the efficiency of the recommendation systems,

the datasets were divided into training and testing

sets. An 80:20 split of the dataset into training and

testing was made to check the effectiveness of the

recommendation system of Netflix (Asreddy,

Shingade, et al., 2019).

3.5

Models Performed

3.5.1

Logistic Regression

The logistic regression can be used to predict the

likelihood that a user will engage with or enjoy a

particular show or movie. This approach involves

framing the recommendation problem as a binary

classification task: given a set of user, item, and

interaction features, the model predicts the

probability of a positive user response (like, watch, or

high rating) (Pathak, Sakore, et al., 2019).

3.5.2

SVM

The Support Vector Machines (SVM) can be used for

the task of categorization or to make a prediction [16]

about user engagement, view preferences, or churn

risks during the analysis of behaviour for users on

Netflix (Jagdale, Khandre, et al., 2021).

A Role of Machine Learning Algorithms for Demand Based Netﬂix Recommendation System

215

3.5.3

Random Forest

Random Forest is an ensemble learning technique,

which is efficient in analysing user behaviour and

forecasting what content a user might like in a Netflix

recommendation engine (Mali, Sawant, et al., 2023).

3.5.4

Singular Value Decomposition (SVD)

It is one of the most useful techniques for developing

dimensional reduction and latent factor discovery to

influence user choices in recommendation systems

like Netflix.

3.5.5

Decision Tree

A more-beloved, if perhaps more interpretable,

machine learning technique is called decision [16]

trees. They work by building a model that, given a

variety of input features-things like user

demographics and content qualities-will predict the

value of a target variable, say user ratings or

preferences, as Netflix and all sorts of

recommendation systems do.

3.5.6

Naive Bayes

Naıve Bayes can be applied in a Netflix

recommendation system by predicting user

preferences for movies or TV shows based on

demographic characteristics and viewing history.

3.5.7

Xg Boost

For supervised learning tasks, such as

recommendation systems like Netflix, XGBoost is the

most popular and effective gradient boosting method

implementation. Its sturdiness against overfitting and

capacity to handle huge datasets make it very

successful.

3.5.8

Cascade Hybrid Model

In complex systems especially, as in Netflix, this

hybrid approach may increase the user’s level of

satisfaction and engagement through multiple models

with their unique advantages but their unique

disadvantages limitations.

3.5.9

Neural Network

Neural networks make it possible to provide highly

customized recommendations by simulating

connections between users and content.

3.5.10

K-Nearest Neighbors

The KNN algorithm is a very simple yet powerful

collaborative filtering tool that Netflix and other

recommendation systems use to present content to

users based on their tastes.

4 RESULTS AND DISCUSSION

This resulted in an accuracy of 68.74% and a Root

Mean Square Error of 0.4560. User preference, to an

extent can be derived through this algorithm; however

the idea should further be augmented with its

application to get closer more accurate predictions.

KNN vs. Gradient Boosting Classifier. Gradually, the

Gradient Boosting Classifier outsmarted the KNN

with an absolute accuracy of 74.65% with the least

RMSE value of 0.4207 as compared to the overall

prediction. With an RMSE of 0.2826, and with the

highest accuracy of 90.66%, Cascade Hybrid was

amazing, showing its capabilities to be able to

produce relevant suggestions.

The clear winner on this one would be the

Singular Value Decomposition because it had the

highest accuracy at 94.34% and had the smallest

RMSE value at 0.2580. What this result reveals is that

SVD could really depict the user preference

accurately. SVM performed quite well with an

accuracy of 75.80% and an RMSE of 0.4108,

although it is still behind models like SVD and

Cascade Hybrid. Decision Tree seems to be less

useful in this situation with an accuracy of 64.70%

and comparatively high RMSE at 0.5942. With an

accuracy of 74.20% and an RMSE of 0.4229,

Random Forest established that recommendations

made were nearly accurate enough. With the neural

network, an accuracy of 73.81% with an RMSE of

0.5099 showed user preferences that can improve.

With the Naive Bayes approach, a moderate capacity

for prediction had an accuracy of 75.03% and an

RMSE of 0.4997.

On the contrary, SVD performed excellently,

yielding an unbelievable accuracy of 94.34% and a

reduced RMSE of 0.2580. Such high accuracy proves

that this is a very successful relevance-based

recommender system as well.

INCOFT 2025 - International Conference on Futuristic Technology

216

Table 1: Performance Comparison of Recommendation

Models.

Model

RMSE

Accuracy (%)

KNN

0.4560

68.74

Gradient Boosting Classifier

0.4207

74.65

Cascade Hybrid

0.2826

90.66

SVD

0.2580

94.34

SVM

0.4108

75.80

Decision Tree

0.5942

64.70

Random Forest

0.4229

74.20

Neural Network

0.5099

73.81

Naive Bayes

0.4997

75.03

Logistic Regression

0.4787

77.09

XG Boost

0.5048

74.52

Figure 4: RMSE for different models.

Improved error performance from lower values of

RMSE is represented by Figure 4, Algorithm RMSE

Comparison. Figure 5 represents Algorithm Accuracy

Comparison on how well each algorithm really

performs and higher values indicate a better predicted

result. In turn, they reflect trade-offs between

accuracy and RMSE in revealing those discrepancies

between algorithms that represent effectiveness Fig. 4

and Fig. 5.

Figure 5: Accuracy for different models.

The scatter diagram in Fig. 6, represents the data onto

two dimensions and showing the result of a K-means

clustering experiment on a data set. The x-axis is

“PCA Component 1,” and the y-axis is “PCA

Component 2,” which is the original multi-

dimensional data projected onto two principal

components to view it.

5 CONCLUSION

In this research, we developed a Netflix

recommendation system model using the Netflix

Recommendation System dataset. Different forms of

suggestion on Netflix had shown how well such

complex algorithms work to enhance user experience

as well as increase viewer engagement, which

ultimately boosts retention rates and revenue growth.

Figure 6: Scatter plot that visualizes the results of a K-means

clustering.

The SVD model alone is proven to be accurate and

efficient in its application on the dataset of Netflix so

well, as it may go in mitigating problems associated

with bespoke content recommendation. Results of

this research are consequential for trends of the

entertainment industry, as well as building more

advanced recommendation systems responding

dynamically to changes in the user’s preference.

Figure 7: Visual representation of Confusion Matrix.

A Role of Machine Learning Algorithms for Demand Based Netﬂix Recommendation System

217

Future research in this direction is expected to extend

beyond these conventional approaches and include

new machine learning techniques, such as deep

learning and reinforcement learning, in order to

increase recommendation prediction accuracy and

real-time adaptability further in diverse streaming

environments, such as that of Netflix. The following

advanced technologies include:

5.1

Context-Aware Suggestions

Through context-aware algorithms, depending upon

the present situations of the users, it can change

suggestions related to the location and time in

addition to considering the device type. It may

increase user engagement when proper suggestions

are brought up at a particular moment in time.

5.2

Multi-Modal Learning

Quality can be improved of recommendations by

researching multi-modal learning strategies that will

combine information from many sources, including

but not limited to text evaluation, photos, and videos.

5.3

Ethical AI

The future research is related to the moral concern of

the recommendation algorithm in Netflix, such as

bias detection and minimization, ensuring fairness,

and also promotion of transparency in the algorithmic

decision- making. XAI methodologies can very well

explain the recommendations. This will increase user

enjoyment and satisfaction.

REFERENCES

P. B. More, A. N. Jadhav, I. Khatik, S. Singh, V. K. Borate

and Y. K. Mali, “Sign Language Recognition Using

Hand Gestures”, 2024 3rd International Conference for

Advancement in Technology (ICONAT), GOA, India,

2024, pp. 1-5, doi:10.1109/ICONAT61936

.2024.10774685.

Y. Mali, M. E. Pawar, A. More, S. Shinde, V. Borate and

R. Shirbhate, “Improved Pin Entry Method to Prevent

Shoulder Surfing Attacks”, 2023 14th International

Conference on Computing Communication and

Networking Technologies (ICCCNT), Delhi, India,

2023, pp. 1-6, doi: 10.1109/ICCCNT569

98.2023.10306875.

Y. K. Mali and A. Mohanpurkar, “Advanced pin entry

method by resisting shoulder surfing attacks”, 2015

International Conference

on Information Processing

(ICIP), Pune, India, 2015, pp. 37-42, doi:

10.1109/INFOP.2015.7489347.

S. A. Nalawade, R. Pattnaik, S. Kadam, P. P. Lodha, Y. K.

Mali and V. K. Borate, “Smart Contract System with

Block-chain Capability for Improving Supply Chain

Management”, 2024 3rd International Conference for

Advancement in Technology (ICONAT), GOA, India,

2024, pp. 1-7, doi: 10.1109/ICONAT61936

.2024.10774955.

S. P. Patil, S. Y. Zurange, A. A. Shinde, M. M. Jadhav, Y.

K. Mali and V. Borate, “Upgrading Energy Productivity

in Urban City Through Neural Support Vector Machine

Learning for Smart Grids”, 2024 15th International

Confe. on Computing Communication and Networking

Technologies (ICCCNT), Kamand, India, 2024, pp. 1-

5, doi: 10.1109/ICCCNT61001.20 24.10724069.

S. Modi, M. Modi, V. Alone, A. Mohite, V. K. Borate and

Y. K. Mali, “Smart shopping trolley Using Arduino

UNO”,2024 15th International Conf. on Computing

Communication and Networking Technologies

(ICCCNT), Kamand, India, 2024, pp.1-6, doi:10.1109/

ICCCNT61001.2024.10725524.

U. Mehta, S. Chougule, R. Mulla, V. Alone, V. K. Borate

and Y. K. Mali, “Instant Messenger Forensic System”,

2024 15th International Conference on Computing

Communication and Networking Technologies

(ICCCNT), Kamand, India, 2024, pp. 1- 6, doi:

10.1109/ICCCNT61001.2024.10724367.

P. Shimpi, B. Balinge, T. Golait, S. Parthasarathi, C. J.

Arunima and Y. Mali, “Job Crafter - The One- Stop

Placement Portal”,2024 15th International Conference

on Computing Communication and Networking

Technologies (ICCCNT), Kamand, India, 2024, pp.1-8,

doi: 10.1109/ICCCNT61001.2024.10725010.

V. Ingale, B. Wankar, K. Jadhav, T. Adedoja, V. K. Borate

and Y. K. Mali, “Healthcare is being revolutionized by

AI-powered solutions and technological integration for

easily accessible and efficient medical care”, 2024 15th

International Confe. on Computing Communication

and Networking Technologies (ICCCNT), Kamand,

India, 2024, pp. 1-6, doi: 10.1109/ICCCNT61001.

2024.10725646.

U. Mulani, V. Nandgaonkar, R. Mulla, S. Sonavane, V. K.

Borate and Y. K. Mali, “Smart Contract System with

Blockchain Capability for Improved Supply Chain

Management Traceability and Transparency”, 2024

15th International Conference on Computing

Communication and Networking Technologies

(ICCCNT), Kamand, India, 2024, pp. 1-7, doi:

10.1109/ICCCNT61001.2024.10723871.

S. Sonawane, U. Mulani, D. S. Gaikwad, A. Gaur, V. K.

Borate and Y. K. Mali, “Blockchain and Web3.0 based

NFT Marketplace”, 2024 15th International Conference

on Computing Communication and Networking

Technologies (ICCCNT), Kamand, India, 2024, pp. 1-

6, doi: 10.1109/ICCCNT61001.2024.10724420.

P. Mandale, S. Modi, M. M. Jadhav, S. S. Khawate, V. K.

Borate and Y. K. Mali, Investigation of Different

Techniques on Digital Actual Frameworks Toward

Distributed Denial of Services Attack, 2024 15th

INCOFT 2025 - International Conference on Futuristic Technology

218

International Conference on Computing 14

Communication and Networking Technologies

(ICCCNT), Kamand, India, 2024, pp. 1-6, doi:

10.1109/ICCCNT61001.2024.10725776.

D. Sengupta, S. A. Nalawade, L. Sharma, M. S. J. Kakade,

V. K. Borate and Y. K. Mali, Enhancing File Security

Using Hybrid Cryptography, 2024 15th International

Conference on Computing Communication and

Networking Technologies (ICCCNT), Kamand, India,

2024, pp. 1-8, doi:

10.1109/ICCCNT61001.2024.10724120.

A. More, S. Khane, D. Jadhav, H. Sahoo and Y. K. Mali,

Auto-shield: Iot based OBD Application for Car Health

Monitoring, 2024 15th International Conference on

Computing Communication and Networking

Technologies (ICCCNT), Kamand, India, 2024, pp.1-

10,doi: 10.1109/ICCCNT61001.2024.10726186.

U. H. Wanaskar, M. Dangore, D. Raut, R. Shirbhate, V. K.

Borate and Y. K. Mali, A Method for Re- identifying

Subjects in Video Surveillance using Deep Neural

Network Fusion, & 2024 15th International Conference

on Computing Communication and Networking

Technologies (ICCCNT), Kamand, India, 2024, pp.1-

4,doi: 10.1109/ICCCNT61001.2024.10726255.

A. More, O. L. Ramishte, S. K. Shaikh, S. Shinde and Y. K.

Mali, Chain-Checkmate: Chess game using

blockchain,2024 15th International Conference on

Computing Communication and Networking

Technologies (ICCCNT), Kamand, India, 2024, pp. 1-

7, doi: 10.1109/ICCCNT61001.2024.10725572.

J. D. Palkar, C. H. Jain, K. P. Kashinath, A. O. Vaidya, V.

K. Borate and Y. K. Mali, Machine Learning Approach

for Human Brain Counselling, 2024 15th International

Conference on Computing Communication and

Networking Technologies (ICCCNT), Kamand, India,

2024, pp. 1-8, doi: 10.1109/ICCCNT61001.2024

.10723852.

M. Dangore, S. Modi, S. Nalawade, U. Mehta, V. K. Borate

and Y. K. Mali, Revolutionizing Sport Education With

AI, 2024 15th International Conf. on Computing

Communication and Networking Technologies

(ICCCNT), Kamand, India, 2024, pp.1-8, doi: 10.1109/

ICCCNT61001.2024.10724009.

M. Dangore, D. Bhaturkar, K. M. Bhale, H. M. Jadhav, V.

K. Borate and Y. K. Mali, &Applying Random Forest

for IoT Systems in Industrial Environments, 2024 15

International Conf. on Computing Communication and

Networking Technologies (ICCCNT), Kamand, India,

2024, pp.1-7, doi: 10.1109/ICCCNT61001.2024.10

725751.

A. More, S. R. Shinde, P. M. Patil, D. S. Kane, Y. K. Mali

and V. K. Borate, Advancements in Early Detection of

Lung Cancer using YOLOv7, 2024 5th International

Conference on Smart Electronics and Communication

(ICOSEC), Trichy, India, 2024, pp. 1739-1746,doi:

10.1109/ICOSEC61587.2024.10722534.

A. O. Vaidya, M. Dangore, V. K. Borate, N. Raut, Y. K.

Mali and A. Chaudhari, Deep Fake Detection for

Preventing Audio and Video Frauds Using Advanced

Deep Learning Techniques, 2024 IEEE Recent

Advances in Intelligent Computational Systems

(RAICS), Kothamangalam, Kerala, India, 2024, pp. 1-

6, doi: 10.1109/RAICS61201.2024.10689785.

Sawardekar, S., Mulla, R., Sonawane, S., Shinde, A.,

Borate, V., Mali, Y.K. (2025). Application of Modern

Tools in Web 3.0 and Blockchain to Innovate

Healthcare System. In: Rawat, S., Kumar, A., Raman,

A., Kumar, S., Pathak, P. (eds) Proceedings of Third

International Conference on Computational Electronics

for Wireless Communications. ICCWC 2023. Lecture

Notes in Networks and Systems, vol 962. Springer,

Singapore. https://doi.org/10.1007/978-981-97-1946-

4_2

Modi, S., Mali, Y., Kotwal, R., Kisan Borate, V., Khairnar,

P., Pathan, A. (2024). Hand Gesture Recognition and

Real-Time Voice Translation for the Deaf and Dumb.

In: Jain, S., Mihindukulasooriya, N., Janev, V.,

Shimizu, C.M. (eds) Semantic Intelligence. ISIC 2023.

Lecture Notes in Electrical Engineering, vol 1258.

Springer, Singapore.https://doi.org/10.1007/978-981-

97-7356-5_35.

Bhongade, A., Dargad, S., Dixit, A., Mali, Y.K., Kumari,

B., Shende, A. (2024). Cyber Threats in Social

Metaverse and Mitigation Techniques. In: Somani,

A.K., Mundra, A., Gupta, R.K., Bhattacharya, S.,

Mazumdar, A.P. (eds) Smart Systems: Innovations in

Computing. SSIC 2023. Smart Innovation, Systems and

Technologies, vol 392. Springer, Singapore. https://doi.

org/10.1007/978-981-97-3690-4_34.

Mali, Yogesh. &TejalUpadhyay, “Fraud Detection in

Online Content Mining Relies on the Random Forest

Algorithm”, SWB 1, no. 3 (2023): 13- 20.

Kale, Hrushikesh, Kartik Aswar, and Dr Yogesh Mali

Kisan Yadav. Attendance Marking using Face

Detection, International Journal of Advanced Research

in Science, Communication and Technology: 417-424.

Inamdar, Faizan, Dev Ojha, C. J. Ojha, and D. Y. Mali. Job

Title Predictor System, International Journal of

Advanced Research in Science, Communication and

Technology (2024): 457-463.

Jagdale, Sudarshan, Piyush Takale, Pranav Lonari,

Shraddha Khandre, and Yogesh Mali. “Crime

Awareness and Registration System, International

Journal of Scientific Research in Science and

Technology 5, no. 8 (2020).

Modi, S., Mali, Y., Sharma, L., Khairnar, P., Gaikwad,

D.S., Borate, V. (2024). A Protection Approach for

Coal Miners Safety Helmet Using IoT. In: Jain, S.,

Mihindukulasooriya, N., Janev, V., Shimizu, C.M. (eds)

Semantic Intelligence. ISIC 2023. Lecture Notes in

Electrical Engineering, vol 1258. Springer, Singapore.

https://doi.org/10.1007/978-981-97-7356- 5_30.

Y. K. Mali, L. Sharma, K. Mahajan, F. Kazi, P. Kar and A.

Bhogle, “Application of CNN Algorithm on X- Ray Images

in COVID-19 Disease Prediction”, 2023 IEEE

International Carnahan Conference on Security

Technology (ICCST), Pune, India, 2023, pp. 1-6, doi:

10.1109/ICCST59048.2023.10726852.

A Role of Machine Learning Algorithms for Demand Based Netﬂix Recommendation System

219

Shabina Modi, “Automated Attendance Monitoring System for

Cattle through CCTV.”, REDVET, vol. 25, no. 1, pp. 1025

-1034, Sep. 2024.

Y. Mali and V. Chapte, “Grid based authentication system”

International Journal of Advance Research in Computer

Science and Management Studies, vol. 2, no. 10, pp. 93- 99,

October 2014.

Rajat Asreddy, Avinash Shingade, Niraj Vyavhare, Arjun

Rokde and Yogesh Mali, “A Survey on Secured Data

Transmission Using RSA Algorithm and Steganography”,

International Journal of Scientific Research in Computer

Science Engineering and Information Technology

(IJSRCSEIT), vol. 4, no. 8, pp. 159-162, September-

October 2019, ISSN 2456–3307.

Jyoti Pathak, Neha Sakore, Rakesh Kapare, Amey Kulkarni and

Prof. Yogesh Mali, “Mobile Rescue Robot”, International

Journal of Scientific Research in Computer Science

Engineering and Information Technology (IJSRCSEIT),

vol. 4, no. 8, pp. 10-12, September- October 2019, ISSN

2456–3307.

Pranav Lonari, Sudarshan Jagdale, Shraddha Khandre, Piyush

Takale and Prof Yogesh Mali, “Crime Awareness and

Registration System”, International Journal of Scientific

Research in Computer Science Engineering and

Information Technology (IJSRCSEIT), vol. 8, no. 3, pp.

287-298, May-June 2021, ISSN 2456–3307.

Yogesh Mali and Nilay Sawant, “Smart Helmet for Coal

Mining”, International Journal of Advanced Research in

Science Communication and Technology (IJARSCT), vol.

3, no. 1, February 2023.

INCOFT 2025 - International Conference on Futuristic Technology

220