According to the World Economic Forum’s Digital Economy, by 2025, it is estimated that 463 exabytes (10^9 bytes) of data will be created each day. This provides fertile ground for identifying factors that help predict asset prices, and machine learning algorithms are uniquely poised to do so. In fact, algorithmic trading already accounts for 60-70% of trades on US stock exchanges. It follows that innovations in factor pricing rests on mining fresh unstructured data with the aid of machine learning algorithms, while at the same time being mindful of sustainable investment and factors that affect climate change.
The goal of this Research Topic is to invite innovative papers on machine learning and factor pricing with applications in finance. Examples of the types of questions we seek to answer include, but are not limited to:
- Does machine learning introduce new paradigms that shed new light on traditional models?
- How can investors benefit from this research?
The scope of the Research Topic may take the form of theoretical papers, applied papers, or critical review papers. Specifically, papers that employ supervised, unsupervised, and/or reinforcement learning are particularly welcome. Theoretical papers that develop algorithms and asymptotic theory for stochastic processes are also encouraged.
Keywords:
asset pricing, risk, perception of risk, factor pricing, data science, rare events, smart beta, Wasserstein distance, benchmark, machine learning, NLP
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
According to the World Economic Forum’s Digital Economy, by 2025, it is estimated that 463 exabytes (10^9 bytes) of data will be created each day. This provides fertile ground for identifying factors that help predict asset prices, and machine learning algorithms are uniquely poised to do so. In fact, algorithmic trading already accounts for 60-70% of trades on US stock exchanges. It follows that innovations in factor pricing rests on mining fresh unstructured data with the aid of machine learning algorithms, while at the same time being mindful of sustainable investment and factors that affect climate change.
The goal of this Research Topic is to invite innovative papers on machine learning and factor pricing with applications in finance. Examples of the types of questions we seek to answer include, but are not limited to:
- Does machine learning introduce new paradigms that shed new light on traditional models?
- How can investors benefit from this research?
The scope of the Research Topic may take the form of theoretical papers, applied papers, or critical review papers. Specifically, papers that employ supervised, unsupervised, and/or reinforcement learning are particularly welcome. Theoretical papers that develop algorithms and asymptotic theory for stochastic processes are also encouraged.
Keywords:
asset pricing, risk, perception of risk, factor pricing, data science, rare events, smart beta, Wasserstein distance, benchmark, machine learning, NLP
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.