Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

We compared the predictive performance of a series of machine learning and traditional methods for monthly CDS spreads, using firms’ accounting-based, market-based and macroeconomics variables for a time period of 2006 to 2016. We find that ensemble machine learning methods (Bagging, Gradient Boosting and Random Forest) strongly outperform other estimators, and Bagging particularly stands out in terms of accuracy. Traditional credit risk models using OLS techniques have the lowest out-of-sample prediction accuracy. The results suggest that the non-linear machine learning methods, especially the ensemble methods, add considerable value to existent credit risk prediction accuracy and enable CDS shadow pricing for companies missing those securities.

Banks and Banking --- Finance: General --- Money and Monetary Policy --- Intelligence (AI) & Semantics --- Model Evaluation and Selection --- Forecasting and Other Model Applications --- Monetary Policy, Central Banking, and the Supply of Money and Credit: General --- Technological Change: Choices and Consequences --- Diffusion Processes --- Financing Policy --- Financial Risk and Risk Management --- Capital and Ownership Structure --- Value of Firms --- Goodwill --- General Financial Markets: General (includes Measurement and Data) --- Monetary economics --- Machine learning --- Financial services law & regulation --- Finance --- Credit default swap --- Credit risk --- Credit ratings --- Stock markets --- Money --- Technology --- Financial regulation and supervision --- Financial markets --- Credit --- Financial risk management --- Stock exchanges --- United States

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

An essential element of the work of the Fund is to monitor and forecast international trade. This paper uses SWIFT messages on letters of credit, together with crude oil prices and new export orders of manufacturing Purchasing Managers’ Index (PMI), to improve the short-term forecast of international trade. A horse race between linear regressions and machine-learning algorithms for the world and 40 large economies shows that forecasts based on linear regressions often outperform those based on machine-learning algorithms, confirming the linear relationship between trade and its financing through letters of credit.

Business and Economics --- Exports and Imports --- Macroeconomics --- Trade: Forecasting and Simulation --- Macroeconomic Aspects of International Trade and Finance: Forecasting and Simulation --- Trade: General --- Energy: Demand and Supply --- Prices --- Macroeconomic Aspects of International Trade and Finance: General --- Empirical Studies of Trade --- International economics --- Oil prices --- Imports --- Exports --- Trade finance --- Trade balance --- International trade --- International finance --- Balance of trade --- Hong Kong Special Administrative Region, People's Republic of China

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

It is always good to have a hypothesis in mind before conducting a research or treating a patient. However, when facing multiple choices of hypotheses, selecting a hypothesis from them would be a wise choice so that resources are not wasted on insignificant things. Experience sampling method is method to collect records from participants about their daily life, and is widely used in researches or clinical treatments to have a comprehensive insight on targeted group of people. In this thesis, adjustments are applied to experience sampling method to optimize it, and the adjusted sampling method is called adaptive experience sampling method. In a context of selecting one hypothesis from two, adaptive experience sampling method is compared with experience sampling method with a simulation study. To start off, one example of adaptive experience sampling method is constructed. Later data is simulated to examine whether adaptive experience sampling method outperforms experience sampling method. Different parameters are also being adjusted in order to enhance the performance of the adaptive experience sampling method. In the end, the scope in which adaptive experience sampling method outperforms the traditional experience sampling method is addressed.