The impact of machine learning on UK financial services

Buchanan, Bonnie; Wright, Danika

doi:10.1093/oxrep/grab016

Cited by 26 publications

(12 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There has been an increasing interest in using computational intelligence and Artificial Intelligence (AI) in financial applications such as asset pricing and derivatives, stock market predictions, algorithmic trading, and credit risk assessment [ 5 , 6 ]. Specifically, machine learning and deep learning technologies started getting many researchers' attention to develop a smarter model for recognizing, predicting, and classifying financial crisis roots [ 7 ] than classical methods that depend on complex calculations as in statistical and operations research approaches [ 8 ]. Compared to classical approaches, AI-based methods have two major strengths in recognizing financial crisis roots.…”

Section: Introductionmentioning

confidence: 99%

RETRACTED ARTICLE: Explainable AI Model for Recognizing Financial Crisis Roots Based on Pigeon Optimization and Gradient Boosting Model

Torky

Gad

Hassanien

2023

Int J Comput Intell Syst

View full text Add to dashboard Cite

Utilizing Artificial Intelligence (AI) techniques to forecast, recognize, and classify financial crisis roots are important research challenges that have attracted the interest of researchers. Moreover, the Explainable Artificial Intelligence (XAI) concept enables AI techniques to interpret the results of processing and testing complex data patterns so that humans can find efficient ways to infer and interpret the logic behind classifying complex data patterns. This paper proposes a novel XAI model to automatically recognize financial crisis roots and interprets the features selection operation. Using a benchmark dataset, the proposed XAI model utilized the pigeon optimizer to optimize the feature selection operation, and then the Gradient Boosting classifier is utilized to recognize financial crisis roots based on the obtained reduct of the most important features. The practical results showed that the short-term interest rates feature is the most important feature by which financial crisis roots can be detected. Moreover, the classification results showed that the built-in Gradient Boosting classifier in the Pigeon Inspired Optimizer (PIO) algorithm achieved training and testing accuracy of 99% and 96.7%, respectively, in recognizing financial crisis roots, which is an efficient and better performance compared to the random forest classifier.

show abstract

Section: Introductionmentioning

confidence: 99%

RETRACTED ARTICLE: Explainable AI Model for Recognizing Financial Crisis Roots Based on Pigeon Optimization and Gradient Boosting Model

Torky

Gad

Hassanien

2023

Int J Comput Intell Syst

View full text Add to dashboard Cite

show abstract

“…Many popular ML models are considered as "black boxes" [7,34], meaning that the inner workings of the algorithms and associated decisions or classifications made are secretive. For example, individual predictions often lack interpretability when predicting a potential customer's risk of discontinuing a telecommunications service.…”

Section: Explainable Artificial Intelligence (Ai) In Churn Analysismentioning

confidence: 99%

Prediction of Customer Churn Behavior in the Telecommunication Industry Using Machine Learning Models

Chang,

Hall,

et al. 2024

Algorithms

View full text Add to dashboard Cite

Customer churn is a significant concern, and the telecommunications industry has the largest annual churn rate of any major industry at over 30%. This study examines the use of ensemble learning models to analyze and forecast customer churn in the telecommunications business. Accurate churn forecasting is essential for successful client retention initiatives to combat regular customer churn. We used innovative and improved machine learning methods, including Decision Trees, Boosted Trees, and Random Forests, to enhance model interpretability and prediction accuracy. The models were trained and evaluated systematically by using a large dataset. The Random Forest model performed best, with 91.66% predictive accuracy, 82.2% precision, and 81.8% recall. Our results highlight how well the model can identify possible churners with the help of explainable AI (XAI) techniques, allowing for focused and timely intervention strategies. To improve the transparency of the decisions made by the classifier, this study also employs explainable artificial intelligence methods such as LIME and SHAP to illustrate the results of the customer churn prediction model. Our results demonstrate how crucial it is for customer relationship managers to implement strong analytical tools to reduce attrition and promote long-term economic viability in fiercely competitive marketplaces. This study indicates that ensemble learning models have strategic implications for improving consumer loyalty and organizational profitability in addition to confirming their performance.

show abstract

“…Such a trend has been registered by recent surveys, showing that credit institutions are gradually embracing ML techniques in different areas of credit risk management, credit scoring and monitoring. [12][13][14] Among all, the biggest annual growth in the adoption of highly performing algorithms has been observed in the SMEs sector. 15 For these reasons, new modeling techniques have been successfully employed in predicting SMEs default, including Deep Learning, 16 Support Vector Machines, 17,18 Neural Networks, 19 and Hazards models, 20,21 to name only a few.…”

Section: Literature Reviewmentioning

confidence: 99%

Lost in a black‐box? Interpretable machine learning for assessing Italian SMEs default

Crosato,

Liberati,

Repetto

2023

Appl Stoch Models Bus & Ind

View full text Add to dashboard Cite

Academic research and the financial industry have recently shown great interest in Machine Learning algorithms capable of solving complex learning tasks, although in the field of firms' default prediction the lack of interpretability has prevented an extensive adoption of the black‐box type of models. In order to overcome this drawback and maintain the high performances of black‐boxes, this paper has chosen a model‐agnostic approach. Accumulated Local Effects and Shapley values are used to shape the predictors' impact on the likelihood of default and rank them according to their contribution to the model outcome. Prediction is achieved by two Machine Learning algorithms (eXtreme Gradient Boosting and FeedForward Neural Networks) compared with three standard discriminant models. Results show that our analysis of the Italian Small and Medium Enterprises manufacturing industry benefits from the overall highest classification power by the eXtreme Gradient Boosting algorithm still maintaining a rich interpretation framework to support decisions.

show abstract

The impact of machine learning on UK financial services

Cited by 26 publications

References 34 publications

RETRACTED ARTICLE: Explainable AI Model for Recognizing Financial Crisis Roots Based on Pigeon Optimization and Gradient Boosting Model

RETRACTED ARTICLE: Explainable AI Model for Recognizing Financial Crisis Roots Based on Pigeon Optimization and Gradient Boosting Model

Prediction of Customer Churn Behavior in the Telecommunication Industry Using Machine Learning Models

Lost in a black‐box? Interpretable machine learning for assessing Italian SMEs default

Contact Info

Product

Resources

About