246 results for machine learning

Corporate Default Forecasting with Machine Learning

Mirko Moscatelli; Simone Narizzano; Fabio Parlapiano et al.

Risk Management Magazine, Vol. 15 No. 3 · 2020 · Italian · DOAJ

We compare statistical models usually employed in credit risk forecasting with machine learning algorithms (ML). Using a large dataset which includes financial ratios and credit behavioral indicators for about 300,000 Italian non-financial firms from 2011 to 2017, we show that training the models…

Classifying Oromo fricatives with machine learning

Feda Negesse

Estudios de Fonética Experimental, Vol. 34 · 2025 · Italian · DOAJ Scopus

Using machine learning, this study investigates how segment duration, spectral moments, and DCT coefficients help differentiating singleton from geminate in Oromo fricatives. Eighteen native Oromo speakers from the western dialect produced speech data consisting of the fricatives in an intervocalic…

Beyond personas. Machine Learning to personalise the project

Niccolò Casiddu; Francesco Burlando; Isabella Nevoso et al.

Agathón, Vol. 12 No. online · 2022 · Italian · DOAJ Scopus

The paper deals with some problems linked to Human-Centred Design (HCD) methods, namely Personas, that may mislead the designers to create distorted and stereotypical representations of users. These archetypal models of ‘human’ are questioned in favour of a data processing approach, that better…

Una introduzione visiva al Machine Learning e al Deep Learning.

Marco Maggesi

Laboratorio dell'ISPF, Vol. 2022 No. XIX · 2022 · Italian · DOAJ

Machine Learning for Credit risk: three successful Case Histories

Paolo Di Biasi; Rita Gnutti; Andrea Resti et al.

Risk Management Magazine, Vol. 17 No. 2 · 2022 · Italian · DOAJ

As the financial services landscape witnesses an unprecedented change, banks can use machine learning (“ML”) to expand their databases through alternative sources providing unstructured and semi-structured information, such as transaction data and digital footprint data. However, ML algorithms also…

Forecasting housing prices in Turkey by machine learning methods

Mehmet Kayakuş; Mustafa Terzioğlu; Filiz Yetiz

Aestimum, Vol. 80 · 2022 · Italian · DOAJ Scopus

In this study, decision tree regression, artificial neural networks (ANN) and support vector machines (SVM) methods are applied by using monthly data for the period 2013-2020 in the estimation of housing sales in Turkey. In the analysis, the volume of individual mortgage loans offered by banks, the…

MACHINE LEARNING CLUSTERING IN FINANCIAL MARKETS: A LITERATURE REVIEW

Marcel BOLOȘ

Annals of the University of Oradea: Economic Science, Vol. 33 No. 1 · 2024 · Italian · DOAJ

Financial knowledge is necessary not only for consumers of banking products and services when purchasing products but also for the unbanked population when they have to decide how much to borrow or save to keep their monthly budget in a comfort zone and to meet medium and long-term financial goals

['Artificial intelligence, machine learning and bibliographic control. DDC Short Numbers - Towards machine-based classifying', 'Artificial intelligence, machine learning and bibliographic control. DDC Short Numbers – Towards machine-based classifying']

Elisabeth Mödden

JLIS.it, Vol. 13 No. 1 · 2022 · Italian · DOAJ Scopus

Defect Detection of Bolts through Machine Learning ofUltrasonic Testing Signals

Abdul Azziz Abd Talib; Chun Yee Lim; Chin Kian Liew

e-Journal of Nondestructive Testing, Vol. 30 No. 3 · 2025 · Italian · DOAJ

…testing personnel qualifications and experience. This paper integrates machine learning to automate ultrasonic testing signal analysis in enhancing the reliability and precision of defect detection of bolts. A-scan signals were analysed to extract key features for machine learning models, with…

ARIMA vs. MACHINE LEARNING IN TERMS OF EQUITY MARKET FORECASTING

Iulian-Cornel LOLEA; Ioan-Radu PETRARIU; Adriana GIURGIU

Annals of the University of Oradea: Economic Science, Vol. 30 No. 2 · 2021 · Italian · DOAJ

…of forecasting, but very few have made comparisons that include ARIMA, machine learning, but also the Prophet forecasting model developed by Facebook, which brought interesting results for certain data series. Based on methodologies validated by other authors, we compared these models in our paper…

Usi intelligenti dell’intelligenza artificiale. Il man-with-the-machine learning

Roberto Trinchero

Journal of Educational, Cultural and Psychological Studies, Vol. 0 No. 30 · 2025 · Italian · DOAJ Scopus

INTELLIGENT USES OF ARTIFICIAL INTELLIGENCE. THE MAN-WITH-THE-MACHINE LEARNING Abstract The use of artificial intelligence systems capable of conversing in natural language with humans and responding to precise inquiries by leveraging a network-powered knowledge base (chatbots) is also expanding…

Machine Learning and Safe and Inclusive Architecture for Fragile Users

Antonio Magarò; Adolfo F. L. Baratta

Agathón, Vol. 5 No. online · 2019 · Italian · DOAJ Scopus

The contribution presents the first results of a research conducted in the Department of Architecture, Roma Tre University, aimed at testing Machine Learning algorithms for train Neural Networks in learning data from BIM, with the purpose of generating Augmented Reality contents. The objective is…

Damage Detection in Railways Through Numerical Simulations and Machine Learning

Ricardo V. Teixeira; Alexandre A. Cury; Flávio S. Barbosa

e-Journal of Nondestructive Testing, Vol. 31 No. 2 · 2026 · Italian · DOAJ

…monitoring systems. The resulting synthetic data can be used to train machine learning models for detecting and localizing structural damage through pattern recognition in the simulated responses. The proposed approach highlights the potential of synthetic data to support the development of…

Detecting information transparency in the italian real estate market: a machine learning approach [Identificare la trasparenza informativa nel mercato immobiliare italiano: un approccio machine learning ]

Laura Gabrielli; Aurora Greta Ruggeri; Massimiliano Scarpa

Valori e Valutazioni, Vol. 31 · 2023 · Italian · DOAJ Scopus

…estate value. The novelty of this research lies in the integrated use of machine learning techniques, computer programming and multi-parametric valuation procedures to understand and manage information opacity in the Italian real estate market, particularly regarding the estimation of the market…

A didactic approach to the machine learning application to weather forecast

Marcello Raffaele; Maria Teresa Caccamo; Giuseppe Castorina et al.

Atti della Accademia Peloritana dei Pericolanti : Classe di Scienze Fisiche, Matematiche…, Vol. 99 No. S1 · 2021 · Italian · DOAJ Scopus

We propose a didactic approach to use the Machine Learning protocol in order to perform weather forecast. This study is motivated by the possibility to apply this method to predict weather conditions in proximity of the Etna and Stromboli volcanic areas, located in Sicily (south Italy). Here the…

New frontiers in financial markets: from machine learning to algorithmic trading

Valentina Lagasio

Risk Management Magazine, Pp 14-18 (2019) · 2019 · Italian · DOAJ

Fintech, Distristributed Ledgers Tecnology (DLT), blockchain, machine learning, algorithmic trading and High Frequency Trading (HFT), are among the most disruptive digital innovations that are transforming the structure of any industrial sector, including the financial industry. Together with the…

Neuro-evolucionismo y deep machine learning: nuevos desafíos para el derecho

Adolfo Jorge Sánchez Hidalgo

Journal of Ethics and Legal Technologies, Vol. 1 No. 1 · 2019 · Italian · DOAJ

…the evolution of the artificial neural system and the method of machine learning. The goal of this writing is to observe the methodology of the modern system of legal argumentation and modern Legal Expert System based on this evolved AI and in the conception deductive of the legal reasoning. In…

Soluzioni di Machine Learning per il Patrimonio Culturale. Il progetto ArtI4EO.

Nais Solutions

Archeomatica, Vol. 15 No. 4 · 2025 · Italian · DOAJ

…of some types of damage present on the surface of the assets. The use of Machine Learning and Deep Learning techniques in the context of monitoring and safeguarding cultural heritage constitutes an important technological advancement. In particular, having automatic tools and methodologies for…

Also available at: DOAJ

Assessing Agricultural Support Policy Impact through Traditional versus Machine-Learning Techniques

Orjon Xhoxhi; Engjell Skreli; Edvin Zhllima et al.

Economia Agro-Alimentare, Vol. 27 No. 3 · 2025 · Italian · DOAJ Scopus

…in Albania, an EU candidate country. By employing both traditional and machine learning methods, the comparative methodological approach represents a notable contribution by enhancing the robustness of the findings, while highlighting the advantages of the random forest algorithm. The research…