Submit Search
Upload
Spotify Stream Prediction using Regression Models
•
0 likes
•
11 views
IRJET Journal
Follow
https://www.irjet.net/archives/V9/i11/IRJET-V9I11151.pdf
Read less
Read more
Engineering
Report
Share
Report
Share
1 of 5
Download now
Download to read offline
Recommended
IRJET- Analysis of Music Recommendation System using Machine Learning Alg...
IRJET- Analysis of Music Recommendation System using Machine Learning Alg...
IRJET Journal
IRJET- Feeling based Music Recommnendation System using Sensors
IRJET- Feeling based Music Recommnendation System using Sensors
IRJET Journal
IRJET- Implementation of Emotion based Music Recommendation System using SVM ...
IRJET- Implementation of Emotion based Music Recommendation System using SVM ...
IRJET Journal
AUTOMATED MUSIC MAKING WITH RECURRENT NEURAL NETWORK
AUTOMATED MUSIC MAKING WITH RECURRENT NEURAL NETWORK
Jennifer Roman
Mood based Music Player
Mood based Music Player
IRJET Journal
Music Genre Classification using Machine Learning
Music Genre Classification using Machine Learning
IRJET Journal
Automated Music Slideshow Generation Using Web Images Based On Lyrics
Automated Music Slideshow Generation Using Web Images Based On Lyrics
Dustin Pytko
Mehfil : Song Recommendation System Using Sentiment Detected
Mehfil : Song Recommendation System Using Sentiment Detected
IRJET Journal
Recommended
IRJET- Analysis of Music Recommendation System using Machine Learning Alg...
IRJET- Analysis of Music Recommendation System using Machine Learning Alg...
IRJET Journal
IRJET- Feeling based Music Recommnendation System using Sensors
IRJET- Feeling based Music Recommnendation System using Sensors
IRJET Journal
IRJET- Implementation of Emotion based Music Recommendation System using SVM ...
IRJET- Implementation of Emotion based Music Recommendation System using SVM ...
IRJET Journal
AUTOMATED MUSIC MAKING WITH RECURRENT NEURAL NETWORK
AUTOMATED MUSIC MAKING WITH RECURRENT NEURAL NETWORK
Jennifer Roman
Mood based Music Player
Mood based Music Player
IRJET Journal
Music Genre Classification using Machine Learning
Music Genre Classification using Machine Learning
IRJET Journal
Automated Music Slideshow Generation Using Web Images Based On Lyrics
Automated Music Slideshow Generation Using Web Images Based On Lyrics
Dustin Pytko
Mehfil : Song Recommendation System Using Sentiment Detected
Mehfil : Song Recommendation System Using Sentiment Detected
IRJET Journal
Turkey music( june 2021).pdf
Turkey music( june 2021).pdf
Srinivas Kanakala
Linear Regression with R programming.pptx
Linear Regression with R programming.pptx
anshikagoel52
IRJET- Musical Instrument Recognition using CNN and SVM
IRJET- Musical Instrument Recognition using CNN and SVM
IRJET Journal
Using R for Classification of Large Social Network Data
Using R for Classification of Large Social Network Data
IJCSIS Research Publications
Predicting movie success from search
Predicting movie success from search
ijaia
Project on nypd accident analysis using hadoop environment
Project on nypd accident analysis using hadoop environment
Siddharth Chaudhary
Automatic Music Generation Using Deep Learning
Automatic Music Generation Using Deep Learning
IRJET Journal
Music Recommendation System
Music Recommendation System
IRJET Journal
DATA MINING USING BUSINESS INTELLIGENCE AND SQL
DATA MINING USING BUSINESS INTELLIGENCE AND SQL
IRJET Journal
Emofy
Emofy
subhashree sahoo
Understanding and Supporting Mobile Application Usage
Understanding and Supporting Mobile Application Usage
Matthias Böhmer
IRJET - Music Generation using Deep Learning
IRJET - Music Generation using Deep Learning
IRJET Journal
IRJET- A Personalized Music Recommendation System
IRJET- A Personalized Music Recommendation System
IRJET Journal
Semantically Enriched Knowledge Extraction With Data Mining
Semantically Enriched Knowledge Extraction With Data Mining
Editor IJCATR
Association Rule Mining using RHadoop
Association Rule Mining using RHadoop
IRJET Journal
IRJET - Automatic Lip Reading: Classification of Words and Phrases using Conv...
IRJET - Automatic Lip Reading: Classification of Words and Phrases using Conv...
IRJET Journal
Innovaccer service capabilities with case studies
Innovaccer service capabilities with case studies
Abhinav Shashank
IRJET- Movie Success Prediction using Popularity Factor from Social Media
IRJET- Movie Success Prediction using Popularity Factor from Social Media
IRJET Journal
Recommendation Engine Powered by Hadoop
Recommendation Engine Powered by Hadoop
Pranab Ghosh
Recommendation Engine Powered by Hadoop - Pranab Ghosh
Recommendation Engine Powered by Hadoop - Pranab Ghosh
BigDataCloud
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
IRJET Journal
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
IRJET Journal
More Related Content
Similar to Spotify Stream Prediction using Regression Models
Turkey music( june 2021).pdf
Turkey music( june 2021).pdf
Srinivas Kanakala
Linear Regression with R programming.pptx
Linear Regression with R programming.pptx
anshikagoel52
IRJET- Musical Instrument Recognition using CNN and SVM
IRJET- Musical Instrument Recognition using CNN and SVM
IRJET Journal
Using R for Classification of Large Social Network Data
Using R for Classification of Large Social Network Data
IJCSIS Research Publications
Predicting movie success from search
Predicting movie success from search
ijaia
Project on nypd accident analysis using hadoop environment
Project on nypd accident analysis using hadoop environment
Siddharth Chaudhary
Automatic Music Generation Using Deep Learning
Automatic Music Generation Using Deep Learning
IRJET Journal
Music Recommendation System
Music Recommendation System
IRJET Journal
DATA MINING USING BUSINESS INTELLIGENCE AND SQL
DATA MINING USING BUSINESS INTELLIGENCE AND SQL
IRJET Journal
Emofy
Emofy
subhashree sahoo
Understanding and Supporting Mobile Application Usage
Understanding and Supporting Mobile Application Usage
Matthias Böhmer
IRJET - Music Generation using Deep Learning
IRJET - Music Generation using Deep Learning
IRJET Journal
IRJET- A Personalized Music Recommendation System
IRJET- A Personalized Music Recommendation System
IRJET Journal
Semantically Enriched Knowledge Extraction With Data Mining
Semantically Enriched Knowledge Extraction With Data Mining
Editor IJCATR
Association Rule Mining using RHadoop
Association Rule Mining using RHadoop
IRJET Journal
IRJET - Automatic Lip Reading: Classification of Words and Phrases using Conv...
IRJET - Automatic Lip Reading: Classification of Words and Phrases using Conv...
IRJET Journal
Innovaccer service capabilities with case studies
Innovaccer service capabilities with case studies
Abhinav Shashank
IRJET- Movie Success Prediction using Popularity Factor from Social Media
IRJET- Movie Success Prediction using Popularity Factor from Social Media
IRJET Journal
Recommendation Engine Powered by Hadoop
Recommendation Engine Powered by Hadoop
Pranab Ghosh
Recommendation Engine Powered by Hadoop - Pranab Ghosh
Recommendation Engine Powered by Hadoop - Pranab Ghosh
BigDataCloud
Similar to Spotify Stream Prediction using Regression Models
(20)
Turkey music( june 2021).pdf
Turkey music( june 2021).pdf
Linear Regression with R programming.pptx
Linear Regression with R programming.pptx
IRJET- Musical Instrument Recognition using CNN and SVM
IRJET- Musical Instrument Recognition using CNN and SVM
Using R for Classification of Large Social Network Data
Using R for Classification of Large Social Network Data
Predicting movie success from search
Predicting movie success from search
Project on nypd accident analysis using hadoop environment
Project on nypd accident analysis using hadoop environment
Automatic Music Generation Using Deep Learning
Automatic Music Generation Using Deep Learning
Music Recommendation System
Music Recommendation System
DATA MINING USING BUSINESS INTELLIGENCE AND SQL
DATA MINING USING BUSINESS INTELLIGENCE AND SQL
Emofy
Emofy
Understanding and Supporting Mobile Application Usage
Understanding and Supporting Mobile Application Usage
IRJET - Music Generation using Deep Learning
IRJET - Music Generation using Deep Learning
IRJET- A Personalized Music Recommendation System
IRJET- A Personalized Music Recommendation System
Semantically Enriched Knowledge Extraction With Data Mining
Semantically Enriched Knowledge Extraction With Data Mining
Association Rule Mining using RHadoop
Association Rule Mining using RHadoop
IRJET - Automatic Lip Reading: Classification of Words and Phrases using Conv...
IRJET - Automatic Lip Reading: Classification of Words and Phrases using Conv...
Innovaccer service capabilities with case studies
Innovaccer service capabilities with case studies
IRJET- Movie Success Prediction using Popularity Factor from Social Media
IRJET- Movie Success Prediction using Popularity Factor from Social Media
Recommendation Engine Powered by Hadoop
Recommendation Engine Powered by Hadoop
Recommendation Engine Powered by Hadoop - Pranab Ghosh
Recommendation Engine Powered by Hadoop - Pranab Ghosh
More from IRJET Journal
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
IRJET Journal
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
IRJET Journal
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
IRJET Journal
Effect of Camber and Angles of Attack on Airfoil Characteristics
Effect of Camber and Angles of Attack on Airfoil Characteristics
IRJET Journal
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
IRJET Journal
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
IRJET Journal
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
IRJET Journal
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
IRJET Journal
A REVIEW ON MACHINE LEARNING IN ADAS
A REVIEW ON MACHINE LEARNING IN ADAS
IRJET Journal
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
IRJET Journal
P.E.B. Framed Structure Design and Analysis Using STAAD Pro
P.E.B. Framed Structure Design and Analysis Using STAAD Pro
IRJET Journal
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
IRJET Journal
Survey Paper on Cloud-Based Secured Healthcare System
Survey Paper on Cloud-Based Secured Healthcare System
IRJET Journal
Review on studies and research on widening of existing concrete bridges
Review on studies and research on widening of existing concrete bridges
IRJET Journal
React based fullstack edtech web application
React based fullstack edtech web application
IRJET Journal
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
IRJET Journal
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
IRJET Journal
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
IRJET Journal
Multistoried and Multi Bay Steel Building Frame by using Seismic Design
Multistoried and Multi Bay Steel Building Frame by using Seismic Design
IRJET Journal
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
IRJET Journal
More from IRJET Journal
(20)
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
TUNNELING IN HIMALAYAS WITH NATM METHOD: A SPECIAL REFERENCES TO SUNGAL TUNNE...
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
STUDY THE EFFECT OF RESPONSE REDUCTION FACTOR ON RC FRAMED STRUCTURE
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
A COMPARATIVE ANALYSIS OF RCC ELEMENT OF SLAB WITH STARK STEEL (HYSD STEEL) A...
Effect of Camber and Angles of Attack on Airfoil Characteristics
Effect of Camber and Angles of Attack on Airfoil Characteristics
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
A Review on the Progress and Challenges of Aluminum-Based Metal Matrix Compos...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Dynamic Urban Transit Optimization: A Graph Neural Network Approach for Real-...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
Structural Analysis and Design of Multi-Storey Symmetric and Asymmetric Shape...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A Review of “Seismic Response of RC Structures Having Plan and Vertical Irreg...
A REVIEW ON MACHINE LEARNING IN ADAS
A REVIEW ON MACHINE LEARNING IN ADAS
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
Long Term Trend Analysis of Precipitation and Temperature for Asosa district,...
P.E.B. Framed Structure Design and Analysis Using STAAD Pro
P.E.B. Framed Structure Design and Analysis Using STAAD Pro
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
A Review on Innovative Fiber Integration for Enhanced Reinforcement of Concre...
Survey Paper on Cloud-Based Secured Healthcare System
Survey Paper on Cloud-Based Secured Healthcare System
Review on studies and research on widening of existing concrete bridges
Review on studies and research on widening of existing concrete bridges
React based fullstack edtech web application
React based fullstack edtech web application
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A Comprehensive Review of Integrating IoT and Blockchain Technologies in the ...
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
A REVIEW ON THE PERFORMANCE OF COCONUT FIBRE REINFORCED CONCRETE.
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Optimizing Business Management Process Workflows: The Dynamic Influence of Mi...
Multistoried and Multi Bay Steel Building Frame by using Seismic Design
Multistoried and Multi Bay Steel Building Frame by using Seismic Design
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Cost Optimization of Construction Using Plastic Waste as a Sustainable Constr...
Recently uploaded
Artificial intelligence presentation2-171219131633.pdf
Artificial intelligence presentation2-171219131633.pdf
Kira Dess
15-Minute City: A Completely New Horizon
15-Minute City: A Completely New Horizon
Morshed Ahmed Rahath
Maximizing Incident Investigation Efficacy in Oil & Gas: Techniques and Tools
Maximizing Incident Investigation Efficacy in Oil & Gas: Techniques and Tools
soginsider
Intro to Design (for Engineers) at Sydney Uni
Intro to Design (for Engineers) at Sydney Uni
R. Sosa
Adsorption (mass transfer operations 2) ppt
Adsorption (mass transfer operations 2) ppt
jigup7320
Software Engineering Practical File Front Pages.pdf
Software Engineering Practical File Front Pages.pdf
ssuser5c9d4b1
UNIT-2 image enhancement.pdf Image Processing Unit 2 AKTU
UNIT-2 image enhancement.pdf Image Processing Unit 2 AKTU
ankushspencer015
Filters for Electromagnetic Compatibility Applications
Filters for Electromagnetic Compatibility Applications
Mathias Magdowski
What is Coordinate Measuring Machine? CMM Types, Features, Functions
What is Coordinate Measuring Machine? CMM Types, Features, Functions
VIEW
analog-vs-digital-communication (concept of analog and digital).pptx
analog-vs-digital-communication (concept of analog and digital).pptx
Karpagam Institute of Teechnology
Involute of a circle,Square, pentagon,HexagonInvolute_Engineering Drawing.pdf
Involute of a circle,Square, pentagon,HexagonInvolute_Engineering Drawing.pdf
JNTUA
engineering chemistry power point presentation
engineering chemistry power point presentation
sj9399037128
5G and 6G refer to generations of mobile network technology, each representin...
5G and 6G refer to generations of mobile network technology, each representin...
archanaece3
Tembisa Central Terminating Pills +27838792658 PHOMOLONG Top Abortion Pills F...
Tembisa Central Terminating Pills +27838792658 PHOMOLONG Top Abortion Pills F...
drjose256
NO1 Best Powerful Vashikaran Specialist Baba Vashikaran Specialist For Love V...
NO1 Best Powerful Vashikaran Specialist Baba Vashikaran Specialist For Love V...
Amil baba
Seismic Hazard Assessment Software in Python by Prof. Dr. Costas Sachpazis
Seismic Hazard Assessment Software in Python by Prof. Dr. Costas Sachpazis
Dr.Costas Sachpazis
handbook on reinforce concrete and detailing
handbook on reinforce concrete and detailing
AshishSingh1301
UNIT 4 PTRP final Convergence in probability.pptx
UNIT 4 PTRP final Convergence in probability.pptx
kalpana413121
Worksharing and 3D Modeling with Revit.pptx
Worksharing and 3D Modeling with Revit.pptx
Mustafa Ahmed
Developing a smart system for infant incubators using the internet of things ...
Developing a smart system for infant incubators using the internet of things ...
IJECEIAES
Recently uploaded
(20)
Artificial intelligence presentation2-171219131633.pdf
Artificial intelligence presentation2-171219131633.pdf
15-Minute City: A Completely New Horizon
15-Minute City: A Completely New Horizon
Maximizing Incident Investigation Efficacy in Oil & Gas: Techniques and Tools
Maximizing Incident Investigation Efficacy in Oil & Gas: Techniques and Tools
Intro to Design (for Engineers) at Sydney Uni
Intro to Design (for Engineers) at Sydney Uni
Adsorption (mass transfer operations 2) ppt
Adsorption (mass transfer operations 2) ppt
Software Engineering Practical File Front Pages.pdf
Software Engineering Practical File Front Pages.pdf
UNIT-2 image enhancement.pdf Image Processing Unit 2 AKTU
UNIT-2 image enhancement.pdf Image Processing Unit 2 AKTU
Filters for Electromagnetic Compatibility Applications
Filters for Electromagnetic Compatibility Applications
What is Coordinate Measuring Machine? CMM Types, Features, Functions
What is Coordinate Measuring Machine? CMM Types, Features, Functions
analog-vs-digital-communication (concept of analog and digital).pptx
analog-vs-digital-communication (concept of analog and digital).pptx
Involute of a circle,Square, pentagon,HexagonInvolute_Engineering Drawing.pdf
Involute of a circle,Square, pentagon,HexagonInvolute_Engineering Drawing.pdf
engineering chemistry power point presentation
engineering chemistry power point presentation
5G and 6G refer to generations of mobile network technology, each representin...
5G and 6G refer to generations of mobile network technology, each representin...
Tembisa Central Terminating Pills +27838792658 PHOMOLONG Top Abortion Pills F...
Tembisa Central Terminating Pills +27838792658 PHOMOLONG Top Abortion Pills F...
NO1 Best Powerful Vashikaran Specialist Baba Vashikaran Specialist For Love V...
NO1 Best Powerful Vashikaran Specialist Baba Vashikaran Specialist For Love V...
Seismic Hazard Assessment Software in Python by Prof. Dr. Costas Sachpazis
Seismic Hazard Assessment Software in Python by Prof. Dr. Costas Sachpazis
handbook on reinforce concrete and detailing
handbook on reinforce concrete and detailing
UNIT 4 PTRP final Convergence in probability.pptx
UNIT 4 PTRP final Convergence in probability.pptx
Worksharing and 3D Modeling with Revit.pptx
Worksharing and 3D Modeling with Revit.pptx
Developing a smart system for infant incubators using the internet of things ...
Developing a smart system for infant incubators using the internet of things ...
Spotify Stream Prediction using Regression Models
1.
International Research Journal
of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 09 Issue: 11 | Nov 2022 www.irjet.net p-ISSN: 2395-0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 721 Spotify Stream Prediction using Regression Models Aakash Kapadia1, Tanvi Khasgiwal2, Leena Kirtikar3, Sanjay Pandey4 1,2,3Student, Information Technology Department, Thadomal Shahani Engineering College, Mumbai 4 Asst. Professor, Dept. Information Technology, Thadomal Shahani Engineering College, Maharashtra, India ---------------------------------------------------------------------***--------------------------------------------------------------------- Abstract - One of the biggest musicplatformsinthe worldis Spotify. With over a 100 million users per day and over 80 million tracks on it, people have been using this music streaming app for multiple things like podcasts, motivational audio and most importantly songs. Spotify is mainly used for songs as most of the worlds renowned artists to publish their content so the world can hear it and enjoy it. Being avid users of Spotify ourselves, we tried to find out what drives the fame of a song – or even try to understand why people listen to a specific song. In this research paper and project, we used multiple algorithms to check what attributes of a song makes it famous and why does it top the weekly charts. This paper uses a Spotify Database and performs Exploratory Data analysis on it to recognize the most influential variables and then further work on them. We have used algorithms like Linear Regression, RandomForest, RidgeRegressionandLasso Regression to compare accuracies of our admired results. Finally, the accuracy will be compared so that we can calculate the approximate streams of a song based on the relevant attributes. Key Words: Spotify, streams, linear regression, ridge regression, random forest, lasso regression. 1. INTRODUCTION We chose a Spotify as our subject because for years as students, we have been using this app to help in various ways. Spotify aides us in entertainment with its millions of songs and several genres. It has many more advantages which makes it a better music app than other appsthatexist. Firstly, it remains of the easiest apps to use and thus multiple age dynamics can be seen as users of the app. Spotify gives a great music sharing experienceasfriendsand family can share songs using a shared account. The app also provides us with a premium version with noadvertisements which enhances the experience by saving the music offline and not using network data to stream it. The biggest advantage is compatibility. It can be used over manydevices including iOS, Android and Windows. Finally, the music collection is what drives people on the app and that’s why mainly the world uses it. We wanted to know why is a song famous, does the artist on the song matter, and what attributes of the song can affect the number of times it has been streamed. To answer our questions, we have implemented the following in our research work: i) Using data visualization plots like bar chart, scatter plot, and heatmap we find the attributes which affect the streams of the song. ii) We then move forward by dropping the attributes like Artist name, Song name, and its release date as in step 1 we realize that they do not affect the streams of a song by a larger scale. iii) Characteristics of a song like Loudness, Popularityofthe song, and its energy were the most contributing factors. iv) Lastly, we take the regression algorithmsmentionedand predict the streams of the song using the relevant factors. 2. LITERATURE REVIEW Authors of research paper [2] investigated the connection between song information, such as key & tempo from the database of Spotify audio properties, and song popularity as determined by the numerous streams of Spotify. They researched four ML algorithms: Linear Regression (LR), Random Forest (RF), K-means, Clustering & created a highly accurate model for predicting success of particular songs. Their research offers a prediction model for figuring out whether a song will be well-liked by the general public and uses machine learning to categorize songs according to how well-liked they are. In [3], Charts Carlos Vicente S. Araujo Marco A. P. Cristo Rafael Guisti make predictions on whether an existing well- liked music will garner greater than normal public interest and go "viral." They also make predictions about whether unexpected jumps in popularity will last over time. They base their conclusions on information from the streaming service Spotify, using "Most Popular" list as a proxy for popularity and its "Virals" list as a proxy for interest increase. Additionally, they take a classification approach to the issue and use a SVM model predicated on famous data to forecast interest and vice versa. Finally, they check to see if acoustic data can be helpful features for both tasks. In [4], Elena Georgieva, Marcella Suta, and Nicholas Burton attempted to foretell which songs will top the Billboard Hot 100. They collected dataset of about four thousand popular & nonpopular songs and used web API of Spotify to extract the audio properties of each song. Using five machine learning algorithms, they were able to predict a song's billboard success with about 75% accuracyonthevalidation
2.
International Research Journal
of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 09 Issue: 11 | Nov 2022 www.irjet.net p-ISSN: 2395-0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 722 set. The two most effective methods were neural network logistic regression. In [5], Rutger Nijkamp’s, study looks into the connection between music information, such as the key and tempo of a song & popularity of song as determined on the basis of number of song’s streams received on Spotify.Theattribute- approach was utilized to investigate the potential explanatory power of song qualities on stream count. 1000 tracks from ten different genres were examined via the Spotify database API. Regression was used to create a prediction model. With this research design, the results indicate that Spotify's audio features have minimal to average explanation power of greater count of stream. 3. METHODOLOGY Methodology section of the paper explores the different methods which we have applied on the Spotify dataset to predict the number of streams of a song. The dataset is used in multiple cases of data visualization and predicting an approximate number. Fig 1 displays a flowchart of the methodology which has been used and implemented in our research and includes data cleaning, its display on graphs and usage of various regression models and obtain appropriate results. Fig. 1. Flow diagram of research work 3.1 Data Collection The data is obtained from [1]. The dataset includes features like song name, artist, artist followers, genre, popularity, danceability, energy, loudness and many more. Fig. 2. Dataset 3.2 Data Preprocessing In this step we remove the inaccurate or null values directly from the .csv file of the dataset which might lead to wrong results. We had to perform less cleaning as the obtained dataset was nearly obsolete. 3.3 Data Visualization Figure 6 shows a heat map of the data which wehaveused to achieve our results. Heatmap map is defined as graphical notation of large volume of data coded by different colours. The heat map takes all the variables present and correlates them with each other at the same time. Figure 7 shows a histogram of number of times a song was charted vs Song Name, figure 8 is a bar chart plotting of an artist vs streams and figure 9 is bar chart reflection of genre and streams. 3.4 Data Analysis On further evaluation of the heatmap, we came to a conclusion that the most prominent features are Loudness and Energy. This can also be verified with the graphs shown in Figure 3 and 4. Figure 3 shows us a scatter plot between popularity and loudness. The graph displays the relation that higher the loudness, higher the popularity of the song. Fig. 3. Popularity Vs Loudness
3.
International Research Journal
of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 09 Issue: 11 | Nov 2022 www.irjet.net p-ISSN: 2395-0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 723 Figure 4 shows a scatter plot betweenpopularityandenergy and it shows that higher the energy of the song, more the popularity. Fig. 4. Popularity Vs Energy Figure 5 displays the regression models we have used with their respective accuracies. The regression model with the most accuracy is random forest. Fig. 5. Accuracy Table Linear Regression is a supervised machine learning algorithm which predicts the target value on the basis of the independent variables provided. According to the accuracies found, we deduced that Linear Regression algorithm would provide us with the best possible results for our dataset. The Hypothesis function of linear regressionisstated below: y = α1 + α2.x … (A) here x denotes input training y = labels to data α1 = intercept α2 = coefficient of x Regression in Random Forest makes use of ensemble learning method. It operates by construction of many decision trees during the training periodand providesusthe mean of the classes as a prediction of all trees. Here LASSO is used acronym of least absolute shrinkages selection operator. Extension of it is penalty term related to cost function. Summation of the coefficients is represented by this phrase. This particular term confine, forcing the model to curtail the value of coefficientsinordertominimize the losses, when the value of coefficients increases from 0 to 1. In contrast to lasso regression, which commonly makes the coefficient absolute zero, ridge regression never puts coefficient value as zeros. The LASSO regressioncombinesstatisticsandMLtoenhance predictability as well as understandability of the resultant model. In essence, a regularised linear regressor is what a ridge regressor is. In other words, we add a regularized term to the initial cost function of the linear regressor in order to drive the learning algorithm to suit the data and help maintain the weights as low as feasible. The 'alpha' parameter of the regularised term controls the regularisation of model, therefore reducing the variance of the estimations. In some conditions where variables are independent & correlated, technique of ridge regression is used for forecasting the coefficients of numerous regressions. Cost Function for Ridge Regressor: Fig. 6. Heat map of Correlation Plot
4.
International Research Journal
of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 09 Issue: 11 | Nov 2022 www.irjet.net p-ISSN: 2395-0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 724 Figure 7 shows that Dance Monkey is the most charted song while Beggin’ is the least charted song. Fig. 7. Histogram of number of times charted Vs Song Name Figure 8 shows that the artists, Maneskin have the highest streams for their song while Bad Bunny has the lowest. Fig. 8. Histogram of Artist Vs Streams Figure 9 shows that the genres, Indie rock Italiano have the highest streams while trap latino has the lowest. Fig. 9. Histogram of Genre Vs Streams 4. CONCLUSION Spotify is a very large platform that is used aroundtheworld every day by millions of users and thus this research project helped us to gain more knowledge about it. It was insightful to know about the attributes that actually affect the streams of a song and what causes a user to listen to a particular artist. Moreover, we gained knowledge about various regression models which can be used for other projects in the future. In this research paper, we have successfully predicted the popularity of songs using relevant attributes, which helped us gaining our desired accuracy. The most influential factors that fulfilled our objective to determine streams were loudness and energy. In the initial part of our research, we have used techniques like Lasso Regression, Ridge Regression, Random Forest and Linear Regression. We have obtained the best results from Random Forest, which came out to be 97.48%, Hence the most accurateregressionmodel was Random Forest. In the future, the research work can be improved with the help of a dataset with more songs and attributes to gain better accuracies of the models. REFERENCES [1] Dataset:https://www.kaggle.com/datasets/sashankpilla i/spotify-top-200-charts-20202021 [2] J. S. Gulmatico, J. A. B. Susa, M. A. F. Malbog, A. Acoba, M. D. Nipas and J. N. Mindoro, "SpotiPred: A Machine Learning Approach Prediction of Spotify Music Popularity by Audio Features," 2022 Second International Conference on Power, Control and Computing Technologies (ICPC2T), 2022, pp. 1-5, doi: 10.1109/ICPC2T53885.2022.9776765. R. Nicole, “Title of paper with only first word capitalized,”J.NameStand. Abbrev., in press. [3] Araujo, C. S., Cristo, M., & Giusti, R. (2019). Predicting music popularity on streaming platforms. Anais Do Simpósio Brasileiro De Computação Musical (SBCM 2019). Available: https://doi.org/10.5753/sbcm.2019.10436 [4] Suta, M. (2018, January 1). Hitpredict: Predicting hit songs using Spotify Data Stanford Computer Science 229:Machinelearning.Academia.edu.Retrieved October 7, 2022. Available: https://www.academia.edu/73249006/Hitpredict_Pred icting_Hit_Songs_Using_Spotify_Data_Stanford_Computer _Science_229_Machine_Learning [5] Nijkamp, R. (n.d.). Prediction of product success: Explaining song popularity by audio features from Spotify data. Retrieved October 6, 2022. Available: https://essay.utwente.nl/75422/1/NIJKAMP_BA_IBA.pd f [6] https://www.statisticshowto.com/lasso-regression/
5.
International Research Journal
of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 09 Issue: 11 | Nov 2022 www.irjet.net p-ISSN: 2395-0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 725 [7] https://towardsdatascience.com/ridge-regression-for- better-usage-2f19b3a202db [8] https://www.analyticsvidhya.com/blog/2021/06/unde rstanding-random-forest/ [9] http://www.stat.yale.edu/Courses/1997- 98/101/linreg.htm [10] https://www.mathworks.com/help/stats/what-is- linear-regression.html
Download now