Home // DATA ANALYTICS 2020, The Ninth International Conference on Data Analytics // View article

Seasonality Modeling Through LSTM Network in Inflation-Indexed Swaps

Authors:
Pier Giuseppe Giribone

Keywords: Inflation-Indexed Swap (IIS); Year-on-Year Inflation-Indexed Swap (YYIIS); Zero-Coupon Inflation-Indexed Swap (ZCIIS); Seasonality model; CPI bootstrap; Machine Learning (ML); Deep Learning; Long Short-Term Memory (LSTM) Network

Abstract:
An Inflation-Indexed Swap (IIS) is a derivative in which, at every payment date, the counterparties swap an inflation rate with a fixed rate. For the calculation of the Inflation Leg cash flows, it is necessary to build a mathematical model suitable for the Consumer Price Index (CPI) projection. For this purpose, quants typically start by using market quotes for the Zero-Coupon swaps in order to derive the future trend of the inflation index, together with a seasonality model for capturing the typical periodical effects. In this study, I propose a forecasting model for inflation seasonality based on a Long Short-Term Memory (LSTM) network: a deep learning methodology particularly useful for forecasting purposes. Thanks to its architecture, able to capture highly nonlinear relationships, and to the design of a careful training, able to satisfy both statistical and econometric features, the proposed methodology can be considered more accurate rather than the traditional one. As a result, the study shows how the CPI predictions, conducted using a FinTech paradigm, can be integrated in the respect of the traditional quantitative finance theory developed in this research field.

Pages: 7 to 12

Copyright: Copyright (c) IARIA, 2020

Publication date: October 25, 2020

Published in: conference

ISSN: 2308-4464

ISBN: 978-1-61208-816-7

Location: Nice, France

Dates: from October 25, 2020 to October 29, 2020