Mathfi-Music © Classifier/Predictive AI


           

     Log in/Register                Request a Demo                Instruction Manual 



A new AI-powered service helping music companies, music scientists and musicians to make better informed decisions whenever a binary or multi-class prediction or classification is required. For example:


1. Predict song popularity: Having extracted and recorded the data features of thousands of past songs including artist, song writer, year of release, month of release, catchy melody (yes or no), easy to remember lyrics (yes or no), repeated chorus (yes or no), predictability score within the first quarter (within song duration), predictability score within the second quarter, predictability score within the third quarter, predictability score within the last quarter, danceability, energy level within the first quarter of the of song, energy within the second quarter, energy within the third quarter, energy within the fourth quarter, key, loudness, mode, speech-ness, acoustic-ness, instrumental-ness, lively-ness, valence, tempo, duration, time signature, class of music (Jazz, country, hip hop, rock, folk music, etc.),  and having verified and labelled each one of those past songs as (not popular: below 0.3333, popular: between 0.3333 and 0.6666, and a hit: above 0.6666, labels and target of prediction), predict the level of popularity of a new song provided that the data features, described above, are available for that song.


2. Music Recommendations: Knowing the past music fans’ demographics, age, gender, location, job, income, social media preferences, past songs listened, the artist they usually listened to,  the frequency they listen to music, the engagement with past recommendations, popularity, danceability, energy, key, loudness, mode, speech-ness, acoustic-ness, instrumental-ness, lively-ness, valence, tempo, duration and time signature of the songs they listened to and other relative data features and knowing what type of music (Jazz, country, hip hop, rock, folk music, etc) they loved most, for a new music fan predict what type of music they are most likely going to be interested in and with what probability.


3. Music genre classifications: Knowing the data features of some music tracks such as artist, popularity, danceability, energy, key, loudness, mode, speech-ness, acoustic-ness, instrumental-ness, lively-ness, valence, tempo, duration, time signature and other relevant data features and knowing what class of music (Jazz, country, hip hop, rock, folk music, etc, the target label of classification) the track belongs to, predict and classify to what class of music a new track belongs to and with what probability.


Or any other binary or multi-class prediction or classification use cases required by music experts or musicians to make decisions.

   

                Log in/Register                Request a Demo                Instruction Manual