The machines have taken over

Mnuchin says the market is overreacting because of algo trading reacting to the Fed comments and the Volcker Rule. Meaning the machines have taken over Wall Street and we cannot do a thing to stop them. He thinks the market (that is, all the algo machines working simultaneously like and ecological system) will rebalance itself.
May be.  I think it will oscillate like stock exchanges in the nineteen century: panics followed by euphoria.

How this machine trading work?

Start with the essential elements such as evaluating datasets, accessing data APIs using Python, using Quandl to access financial data, and managing prediction errors. You’ll then cover various machine learning techniques and algorithms that can be used to build and train algorithmic models using pandas, Seaborn, StatsModels, and scikit-learn. You will build, estimate, and interpret AR(p), MA(q), and ARIMA(p, d, q) models using StatsModels. You will apply Bayesian prior, evidence, and posterior concepts to distinguish uncertainty using PyMC3. You’ll then utilize Natural Language Toolkit (NLTK), scikit-learn, and spaCy to assign sentiment scores to financial news and classify documents to extract trading signals. As you make your way through the chapters, you’ll design, build, tune, and evaluate feed-forward neural networks, recurrent neural networks, and convolutional neural networks (FFNNs, RNNs, and CNNs) using Keras to design sophisticated algorithms. You’ll also apply transfer learning to satellite image data to predict economic activity. Then you’ll apply reinforcement learning for optimal trading results.