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 benefi...

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: Quantitative research; Computational finance; Semantically meaningful sentence embeddings; Responsible Research and Innovation; Justification mining; Correlation between sentiment and stock returns; Quant finance; Algorithmic trading; Natural language processing; Clustering models; Financial text; Deep learning transformer models; Sentence embeddings; Motivations behind machine learning predictions; Model interpretability; AI explainability
• Subjects: Quantitative research; Computational finance; Machine learning; Supervised learning (Machine learning); Natural language processing (Computer science); Financial engineering; Ensemble learning (Machine learning); Finance; Quantitative analysts; Support vector machines; Algorithmic trading; Transfer learning (Machine learning); Trading rooms (Finance); Deep learning (Machine learning); Sentiment analysis