Forecasting the negative feedback loop with machine learning techniques

Ceravolo, Laura Isabella Elena (A.A. 2020/2021) Forecasting the negative feedback loop with machine learning techniques. Tesi di Laurea in Advanced financial economics, Luiss Guido Carli, relatore Paolo Porchia, pp. 55. [Master's Degree Thesis]

[img] PDF (Full text)
Restricted to Registered users only

Download (930kB) | Request a copy


Understanding the perverse feedback loop. A historical overview of sovereign debt crises. The feedback loop: banking crises as cause of sovereign debt crisis. The feedback loop: sovereign debt crisis as cause of bank crisis. The feedback loop: sovereign debt crisis and moral hazard. The dataset. Data sources, countries and time coverage. Real sector: real GDP, employment rate, output gap (% GDP) and openness. Government debt sustainability: current account balance, primary balance and fiscal balance. The analytical toolkit: linear models: logistic classification with LASSO regularization. Linear models: Kernel support vector machines. Dendrological methods: decision trees. Dendrological methods: random forests. Dendrological methods: extreme trees. Artificial neural networks: multilayer perceptrons for classification. Experimental procedure. Baseline model comparison. Widening the eyes of the machine: synthetic dataset creation. Forecast based on the subset 2006-2017. Possible implementations of the synthetic data generative model. An interpretation with the Shapley values. The Shapley values: an introduction. Explore the extreme trees.


Bibliografia: pp. 51-52.

Thesis Type: Master's Degree Thesis
Institution: Luiss Guido Carli
Degree Program: Master's Degree Programs > Master's Degree Program in Economics and Finance (LM-56)
Chair: Advanced financial economics
Thesis Supervisor: Porchia, Paolo
Thesis Co-Supervisor: Santucci de Magistris, Paolo
Academic Year: 2020/2021
Session: Summer
Deposited by: Alessandro Perfetti
Date Deposited: 16 Mar 2022 15:49
Last Modified: 16 Mar 2022 15:49


Downloads per month over past year

Repository Staff Only

View Item View Item