Automatic Feature Engineering (AFE) aims to extract useful knowledge for interpretable predictions given data for the machine learning tasks. Here, we develop AFE to extract dependency relationships that can be interpreted with functional formulas to discover physics meaning or new hypotheses for the problems of interest. We focus on materials science applications, where interpretable predictive modeling may provide principled understanding of materials systems and guide new materials discovery. It is often computationally prohibitive to exhaust all the potential relationships to construct and search the whole feature space to identify interpretable and predictive features. We develop and evaluate new AFE strategies by exploring a feature generation tree (FGT) with deep Q-network (DQN) for scalable and efficient exploration policies. The developed DQN-based AFE strategies are benchmarked with the existing AFE methods on several materials science datasets.

Streaming media, as a brand new carrier of cultural products, plays a very important role in business and culture under the rapid development of the Internet. In the wake of the pandemic, many media industries and companies have been affected. First and foremost is Netflix. With the development of the epidemic, Netflix’s market share continues to eat up the market share of film and television. This paper will first study some problems encountered by Netflix after the epidemic and what caused its market value to decline. In addition, this paper will predict and research its future strategies and analyze Netflix by connecting with the global streaming media industry. This article aims to help some small streaming media companies to solve the problems they encounter after the epidemic. And These companies can learn from Netflix’s solutions to some extent and also drive the development of the streaming media industry from the side.