Alternative Data: Sentiment Analysis in Machine-Learning Finance скачать в хорошем качестве

Alternative Data: Sentiment Analysis in Machine-Learning Finance

The conversation with Christian Borch (University of Copenhagen) and Kristian Bondo Hansen (Copenhagen Business School) about their recent essay, “Alternative data and sentiment analysis: Prospecting non-standard data in machine learning-driven finance,” Big Data & Society (January 2022) was livestreamed to the public on Thursday 10 November at 4 PM EST. Social media commentary, satellite imagery and GPS data are a part of ‘alternative data’, that is, data that originate outside of the standard repertoire of market data but are considered useful for predicting stock prices, detecting different risk exposures and discovering new price movement indicators. With the availability of sophisticated machine-learning tools, alternative data are gaining traction within the investment management and algorithmic trading industries. Hansen and Borch's paper shows that social media-based sentiment analytics is one manifestation of how alternative data are deployed for stock price prediction purposes. Christian Borch is a Professor of Sociology at the University of Copenhagen working at the intersection of the sociology of financial markets and the sociology of technology. His recent work examines the role of machine learning systems in financial markets, using these markets as a laboratory for understanding the sociological impact of machine-learning systems more broadly. Kristian Bondo Hansen is a Postdoctoral Fellow in the Department of Management, Society and Communication at Copenhagen Business School. His research examines the use of big data and machine learning techniques in various industries and organizational settings and the socio-economic and ethical implications of the quantification and datafication of society. Presented by Platform Economies Research Network at The New School and ADM+S.