Search Results - subject:"algorithm"

Bandits for Algorithmic Trading with Signals

Cartea, Álvaro; Drissi, Fayçal; Osselin, Pierre - 2023

uses a new contextual bandit algorithm, which we call MTGP-LR, to learn the reward functions that map features to trading … algorithm employs a new online change-point detection test to learn in non-stationary environments. As an application in optimal …

Persistent link: https://www.econbiz.de/10014353755

Short-Run Price Efficiency and Discovery of Algorithmic Traders : A Machine Learning Approach

Curran, Edward; Hunt, Jack; Mollica, Vito - 2023

This paper examines the short-run weak-form efficiency of equities, using a proprietary data set permitting analysis of orderbook characteristics to measure short-term price predictability. The results show that high levels of algorithmic trader activity in a stock lowers the level of short-run...

Persistent link: https://www.econbiz.de/10014353854

From Predictive Algorithms to Automatic Generation of Anomalies

Mullainathan, Sendhil; Rambachan, Ashesh - 2023

We ask how machine learning can change a crucial step of the scientific process in economics: the advancement of theories through the discovery of "anomalies." Canonical examples of anomalies include the Allais Paradox and the Kahneman-Tversky choice experiments, which are concrete examples of...

Persistent link: https://www.econbiz.de/10014354788

Identifying Financial Crises Using Machine Learning on Textual Data

Chen, Mary; DeHaven, Matthew; Kitschelt, Isabel; Lee, … - 2023

We use machine learning techniques on textual data to identify financial crises. The onset of a crisis and its duration have implications for real economic activity, and as such can be valuable inputs into macroprudential, monetary, and fiscal policy. The academic literature and the policy realm...

Persistent link: https://www.econbiz.de/10014354923

Trade-Offs in the Design of Financial Algorithms

Gaudeul, Alexia; Giannetti, Caterina - 2023

algorithm.They then choose whether to adopt it. We vary the algorithm in terms of its trading strategy and whether its decisions … can be overriden or not. We find that adoption rates are low, but investors are more likely to adopt an algorithm that …, does not consistently affect algorithm take-up. Rather, algorithm adoption depends mainly on how successful a trader was …

Persistent link: https://www.econbiz.de/10014355154

Combining Algorithmic and Stochastic Data Models

Francke, Marc; Van de Minne, Alex - 2023

, location value, and property random effects for properties that sold more than once. The machine learning algorithm will fit …

Persistent link: https://www.econbiz.de/10014356050

Trusted and Trustworthy Algorithmic Fiduciaries

Li, Yuning - 2023

The Digital Age is speedily transforming into the Algorithmic Age, where algorithms carry on or contribute to a significant number of important social, economic, and technical decision-making. Apart from platform dominance, private governance, and surveillance capitalism, private and public use...

Persistent link: https://www.econbiz.de/10014356233

Online Appendix of 'Steering via Algorithmic Recommendations'

Chen, Nan; Tsai, Hsin-Tien - 2023

Online Appendix of “Steering via Algorithmic Recommendations” Chen and Tsai (2019)This paper studies whether self-preferencing affects algorithmic recommendations on dominant platforms. We focus on the dual role of Amazon.com as a platform owner and retailer. We find that products sold by...

Persistent link: https://www.econbiz.de/10014357591

Machine Learning : Models And Algorithms

Bloch, Daniel Alexandre - 2023

This textbook introduces the mathematical models and algorithms utilised in machine learning, covering supervised and unsupervised learning as well as reinforcement learning: In supervised learning we present ensemble models, artificial neural networks, deep neural networks, recurrent neural...

Persistent link: https://www.econbiz.de/10014357746

Algorithms and Artificial Intelligence : A Criticism of Their Implementation in the Modern Workplace as It Relates to Employment Law

Oprescu-Havriliuc, Nicholas - 2023

From the dawn of civilisation, automation and innovation have been at the forefront of society. At present, employers are eagerly looking for ways to optimise work and production processes. While AI has the potential to transform work and workplaces, displace jobs, create new jobs, and impact...

Persistent link: https://www.econbiz.de/10014357775