Deep Learning in Finance: A Survey of Applications and Techniques

Published: Aug. 20, 2024

Machine learning (ML) has transformed the financial industry by enabling advanced applications such as credit scoring, fraud detection, and market forecasting. At core of this transformation is deep (DL), a subset ML that robust at processing analyzing complex large datasets. This paper provides concise overview key models, including Convolutional Neural Networks (CNNs), Long Short-Term Memory networks (LSTMs), Deep Belief (DBNs), Transformers, Generative Adversarial (GANs), Reinforcement Learning (Deep RL). The study examines their processes, mathematical foundations, practical in finance. It also explores recent advances emerging trends alongside critical challenges data quality, model interpretability, computational complexity, offering insights into future research directions can guide development more explainable models.

Language: Английский

---

Causal aware parameterized quantum stochastic gradient descent for analyzing marketing advertisements and sales forecasting

Information Processing & Management, Journal Year: 2023, Volume and Issue: 60(5), P. 103473 - 103473

Published: Aug. 8, 2023

Language: Английский

---

An Unsupervised Anomaly Detection Based on Self-Organizing Map for the Oil and Gas Sector

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(6), P. 3725 - 3725

Published: March 15, 2023

Anomaly detection plays a crucial role in preserving industrial plant health. Detecting and identifying anomalies helps prevent any production system from damage failure. In complex systems, such as oil gas, many components need to be kept operational. Predicting which parts will break down time interval or ones are working under abnormal conditions can significantly increase their reliability. Moreover, it underlines how the use of artificial intelligence is also emerging process industry not only manufacturing. particular, state-of-the-art analysis reveals growing interest subject that most identified algorithms based on neural network approaches various forms. this paper, an approach for fault identification was developed using Self-Organizing Map algorithm, results obtained map intuitive easy understand. order assign each node output single class unique, purity examined. The samples mapped two-dimensional space, clustering all readings into six macro-areas: (i) steady-state area, (ii) water anomaly macro-area, (iii) air-water (iv) tank (v) air (vi) transition area. through confusion matrix, found algorithm achieves overall accuracy 90 per cent classify recognize state system. proposed tested experimental at Università Politecnica delle Marche.

Language: Английский

---

AIDA-Based Customer Segmentation With User Journey Analysis for Wi-Fi Advertising System

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 111468 - 111480

Published: Jan. 1, 2024

Customer segmentation is an important aspect in aiding businesses to comprehensively understand their customer base and tailor marketing strategies for optimal effectiveness. Traditional approaches have predominantly concentrated on demographic factors observable characteristics. However, these limitations that prevent them from capturing the intricate user journeys of each identified segment. Hence, this paper proposes approach using clustering algorithms, specifically K-Means, BIRCH, Gaussian Mixture Model dataset derived Wi-Fi advertising system, with a focus tracking progression through stages AIDA (Attention, Interest, Desire, Action) Model. This not only presents AIDA-based metric designed data, it also strives measure different journey analysis. Through combination main objective gain nuanced understanding distinct characterizing within further incorporates dynamic-characteristics range table delineate weak strongly engaged behavioral traits, thereby demonstrating efficacy combining algorithms unraveling insights into behavior across diverse segmented group. Based detailed levels segment, suggests actionable enhance by identifying which emphasize, ultimately leading improved campaign effectiveness satisfaction.

Language: Английский

---

Finetuning Analytics Information Systems for a Better Understanding of Users: Evidence of Personification Bias on Multiple Digital Channels

Information Systems Frontiers, Journal Year: 2023, Volume and Issue: 26(2), P. 775 - 798

Published: April 22, 2023

Abstract Although the effect of hyperparameters on algorithmic outputs is well known in machine learning, effects information systems that produce user or customer segments are relatively unexplored. This research investigates varying number personification engagement data a real analytics system, employing concept persona. We increment personas from 5 to 15 for total 330 and 33 persona generations. then examine changing hyperparameter gender, age, nationality, combined gender-age-nationality representation population. The results show despite using same algorithm, strongly biases system’s selection 990 an average deviation 54.5% 42.9% 28.9% 40.5% gender-age-nationality. A repeated analysis two other organizations shows similar all attributes. occurred platforms attributes, as high 90.9% some cases. imply decision makers should be aware set they exposed to. Organizations looking effectively use must wary altering could substantially change results, leading drastically different interpretations about actual base.

Language: Английский

---