4. Requirements
To predict the next upcoming song for Salsa,
Bachata, or Kizomba concert or event, we need to
consider the tempo, rhythm, mood, and lyrics of the
current song playing. Also, it's essential to choose a
song that is popular among the audience or a classic
song that is known to be a crowd-pleaser.
By considering these factors, we need to predict the
next song that will keep the audience engaged and
maintain the energy level of the event.
5. Solution Proposed
The code which makes a machine learning model that uses the random forest algorithm to predict the
popularity of new songs.
The first part of the code loads a CSV file containing information about various songs, such as song title, genre,
popularity, next song popularity, and song duration. Creates a bar chart to display the popularity of each type.
Creates a scatterplot to show the relationship between the current song's popularity and the next song's
popularity.
6.
7. Solutions Met So Far
The model is trained using a 100 estimators random forest
regressor and the accuracy of the model is calculated by
comparing the predicted values with the actual values in
the test set.
The project estimates the popularity of new songs using
the trained model, picks a random song with the predicted
popularity, and displays its characteristics.
This project uses a time loop to estimate the popularity of
100 new songs and waits one second between each
guess.
8. Challenges
Without a dataset ideal for estimating
the next song, we strained to adapt the
algorithm to match the data we
obtained at the end of the research or
collected from Spotify.
9. Roadmap
2023
Q1 — On Track
Re-calibrate marketing team spend
Q1 — Research and gain knowledge
Q2 — Prepare a playlist Dataset
Q3 — Be flexible with variety of songs
Q4 — Entertaining event for the audience.
10. Current Priorities
Only the estimated song values are
being decoded and written on the
screen; So, we are trying to implement a
music's that will be played in real time.