Justification Mining: Developing a novel machine learning method for identifying representative sentences and summarising sentiment in financial text

Thesis

As the fields of machine learning, natural language processing, and big data become increasingly important throughout various industries, including finance, it becomes crucial to evaluate how they are being utilised and understand the motivations behind the recommendations of algorithms, in order to make sound decisions based on this information. In finance, particularly, being able to create concise and easy to comprehend tools for understanding machine learning models is extremely b...

Expand abstract

Authors: Patel, K

• DOI: 10.5287/ora-bxojbbpyy
• Type of award: DPhil
• Level of award: Doctoral
• Awarding institution: University of Oxford
• Language: English
• Keywords: Quant finance; Quantitative research; Semantically meaningful sentence embeddings; Algorithmic trading; Deep learning transformer models; Model interpretability; Motivations behind machine learning predictions; Correlation between sentiment and stock returns; Natural language processing; Clustering models; Justification mining; Sentence embeddings; AI explainability; Responsible Research and Innovation; Financial text; Computational finance
• Subjects: Ensemble learning (Machine learning); Computational finance; Quantitative analysts; Quantitative research; Algorithmic trading; Support vector machines; Trading rooms (Finance); Deep learning (Machine learning); Machine learning; Financial engineering; Transfer learning (Machine learning); Finance; Sentiment analysis; Supervised learning (Machine learning); Natural language processing (Computer science)