Angela  Dickens

Angela Dickens


AI-powered Music Production in Music Streaming

“Creating an intelligence that can talk about you from the instruments you own.”

Master Article


Creating the Physical to Virtual KPI for the previous article and making an automated analysis decision based on the artist’s instrumentation.

To understand the interaction of an artist with their song, we need to understand their instruments. To understand their instruments we need a way to fetch their instruments and create a dataset.

Web scraping the Data

Equipboard is a website that serves as a database for the instruments that artists use. The entire database is crowdsourced. The sources vary from

YouTube videos to news articles to interviews. It covers a large spectrum of vision.

The following tools were used to scrape data of artists that had an image on Equipboard (the general assumption was that if the artist were reputed and large enough they would have an image, hence better data quality)

  • Python was used as a commander to coordinate the scraping.
  • Chrome was used to view the Equipboard web pages.
  • Selenium automated the chrome browser to browse all artists.
  • Beautiful Soup helped in extracting the data from the HTML page source.

All categories were captured for 1834 artists. The sample being indicative of the artist population of the world.

Cleaning and Analysing the Data

Correlation Analysis — Here, I am trying to see if a correlation is present among certain kinds of instruments, because of the number of columns it made sense to program the plots to be interactive.

Dividing the correlation plots into increments of 0.1 helped to infer the results,

  • A negative correlation was not observed. (Musicians are hearty to all instruments!)
  • Cellos/Upright Basses & Drums/Drum Sticks/Drum Hardware had a strong (>0.80) positive correlation.
  • Studio Equipment/ Keyboards and Synthesizers & Studio Monitors/ Headphones had a moderate (>0.60) positive correlation.
  • DAWs had a positive correlation (>0.50) with Software Instruments and Plugins and Studio Monitors
  • I’m not considering correlations below 0.50 because looking at the data from a music producer and artist’s perspective there doesn’t seem to be much causal behavior.

This is how the instrument buckets distribution looks like,

  • _Virtual _— Purely Virtual Instruments.
  • ‘Virsical’ — A mix of physical and virtual instruments. (This will create our abstraction context!)
  • Physical — Purely physical instruments.
  • Misc — Extra music/non-music gear of the artist.
  • Interface — Parallel to Virsical instruments but serve more as physical connectors.

Let’s look at the compressed correlation.

Key observations,

  • Physical and Virtual Instruments are not correlated! These can, in fact, be separate columns in our matrix.
  • Virsical and Interface buckets seem to have a mild correlation to software instruments but very little correlation to the Physical bucket (this is expected, a MIDI device needs a software, however, a guitarist doesn’t always need a software, he can do by with an Amp, hence a mild correlation). Keeping this in mind we will have to normalize our weightage for our Interface variable.
  • I will not be considering the Misc Bucket for our analysis because it includes non-musical gear like caps and baby groots etc.

#data-science #music-analysis #data-analytics #data analysis

What is GEEK

Buddha Community

AI-powered Music Production in Music Streaming

Aleks Shamles


This is an interesting idea that many people may like. In general, I would like to note that it is very interesting to find new discoveries that can help you in something. For example, I recently realized that there is a great genre of house music that I heard on a great platform for musicians who would help to get attached to the site.

Create Music Streaming App Like Spotify

Interested in music application development like Spotify? We at AppClues Infotech help to build online music streaming and podcast apps like Spotify for iOS and Android. Hire our best designers & developers to build your own music streaming app like Spotify with customized features & functionality.

For more info:
Call: +1-978-309-9910

#create music streaming app like spotify #create music streaming app like spotify #create music streaming app like spotify #hire music streaming app developers #cost to make a music streaming app #cost to make an app like spotify

On-Demand Music Streaming App I Live Streaming App Development Company

On-Demand Live Streaming App Development Company- Create on-demand music streaming apps with hi-tech Music streaming portal and app development experts.

#music streaming app development #music streaming app development company #music streaming software development #create music streaming app #live streaming app development

Obie  Rowe

Obie Rowe


Learning When and When Not to Leverage AI in Your Products

You need to go from your house to the Airport. Do you take a Limo or a bike? Of course a Limo? The road is bad and the traffic worse… A Limo is not always the right choice.

Product Managers solve user problems. Sometimes AI is the answer to all your problems. Other times, it is not worth the trouble.

The question becomes, when and where should we leverage AI in our Products?

My first job as a Product Manager was in an AI based startup whose core competency was image and video based analytics. I was exploring the feasibility and applications in the Security Surveillance space.

What I found surprised me.

One of my visits was to a company helping the Singapore govt with the Surveillance of the country. Singapore has one of the finest infrastructures of the world. And it maintains it beautifully. Littering is a punishable offence. One aspect, hence also becomes ensuring that people don’t throw garbage from the balconies of their highrise buildings.

The few rooms had its walls completely plastered with hundreds of screens. Around 1 person per wall was busily looking at multiple screens at a time trying to detect violations. 24X7 monitoring across thousands of cameras was not an easy task.Was it practical? I would say no, not if done manually.

So here is how they handled it.

They added pixel monitors on each of the balcony railings within range. Any pixel changes flagged the image and people would set forth to manually analyze them.

There were two main problems. First, this was, of course, not scalable. Second, There were too many false positives. Anyone randomly roaming around in their balcony would trigger the alarm. Needless to say, this was very expensive to implement. That was when I was convinced that an AI could do this better and more effectively.

Just like this use case, there are many problems that could be solved by AI.

But what are those problems? When do you even dabble with AI to solve your problems.

It is worth a serious consideration because AI is not without its limitations and challenges. AI done wrong often leads to extremely high costs without the added value. Un-Explainability of results and inconsistent responses are other factors often hampering the reliability.

So, what are some guidelines that will help you decide if to go the AI route.

Do not use AI if:

  • Your problems can be solved by simple rules
  • If you need an explanation of why you received the output that you did. AI is often unexplainable.
  • You need a 100% accuracy 100% times
  • If you do not have good quality and quantity of data
  • If your product includes one or more of the following problems, you could leverage AI

1. Ranking and recommendation

When you visit Amazon app with an intention to buy a product, it is important to Amazon that you make a purchase. With thousands of Products in a single category, how does Amazon shows you the product that you will like? It hence utilizes your behavioral patterns, the characteristic of products, and other parameter to predict the products you are likely to purchase. It can do so without AI as well, but then keeping a track of your changing preferences, purchasing patterns need constant adaptation. AI hence solves this problem beautifully.

#product-management #artificial-intelligence #business #ai #ai-applications #when-to-use-ai #product #hackernoon-top-story

Otho  Hagenes

Otho Hagenes


Making Sales More Efficient: Lead Qualification Using AI

If you were to ask any organization today, you would learn that they are all becoming reliant on Artificial Intelligence Solutions and using AI to digitally transform in order to bring their organizations into the new age. AI is no longer a new concept, instead, with the technological advancements that are being made in the realm of AI, it has become a much-needed business facet.

AI has become easier to use and implement than ever before, and every business is applying AI solutions to their processes. Organizations have begun to base their digital transformation strategies around AI and the way in which they conduct their business. One of these business processes that AI has helped transform is lead qualifications.

#ai-solutions-development #artificial-intelligence #future-of-artificial-intellige #ai #ai-applications #ai-trends #future-of-ai #ai-revolution

Teresa  Jerde

Teresa Jerde


Spark Structured Streaming – Stateful Streaming

Welcome back folks to this blog series of Spark Structured Streaming. This blog is the continuation of the earlier blog “Internals of Structured Streaming“. And this blog pertains to Stateful Streaming in Spark Structured Streaming. So let’s get started.

Let’s start from the very basic understanding of what is Stateful Stream Processing. But to understand that, let’s first understand what Stateless Stream Processing is.

In my previous blogs of this series, I’ve discussed Stateless Stream Processing.

You can check them before moving ahead – Introduction to Structured Streaming and Internals of Structured Streaming

#analytics #apache spark #big data and fast data #ml #ai and data engineering #scala #spark #streaming #streaming solutions #tech blogs #stateful streaming #structured streaming