Machine Learning used to be really expensive
Once upon a time, if you wanted to implement a machine learning project, besides from an exploitable dataset, you also needed two things:
- An incredibly expensive salary (over $300K) to hire a ML expert, specialised in a particular field (deep learning, convolutional neural networks, etc)
- Huge and very expensive IT infrastructure, specially to do the parallel computing required to train ML models.
Both these elements made it impossible for normal companies to implement Machine Learning in their every day operations and ML was reserved to only the wealthiest corporations in the world.