TY - GEN
T1 - An Investigation of the Relationship Between Expected Inflation and the Actual Inflation Using Historical Financial Indices
AU - Hashemi, Ray R.
AU - Ardakani, Omid M.
AU - Miller, Brandon
AU - Bahrami, Azita G.
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
PY - 2025
Y1 - 2025
N2 - The University of Michigan and the Federal Reserve Bank of Cleveland separately report inflation expectation metrics that measure what consumers in the United States expect actual inflation (AINF) to be for different time horizons, including 1-year (UMI1 and UST1). This research investigates the following hypothesis: UMI1/UST1 can predict AINF (with an accuracy of >60%) using historical financial indices of: 30-year fixed rate mortgage average, National Home Price Index, Oil Price, unemployment rate, and money supply growth. Collected data [1990-01-01 to 2022-03-01] partially coincided with the Great Recession and the COVID-19 pandemic. To isolate the affected data, five partitions of Calm1, Chaos1, Calm2, Chaos2, and ALL were created. The first and second pairs contain data for the period “before” and “during” the two events, respectively, and the last partition contains all data. Each partition has UMI1 and UST1 versions. The greedy-reduct for each of the ten training sets was identified. Rules were extracted from the reducts using Rough Sets (RS), Association Analysis (AA), and Learning by Example (LE) approaches. The application of the generalized rules on corresponding test sets reveals that AA and RS rules delivered the worst and best performances with six and zero hypothesis rejections, respectively.
AB - The University of Michigan and the Federal Reserve Bank of Cleveland separately report inflation expectation metrics that measure what consumers in the United States expect actual inflation (AINF) to be for different time horizons, including 1-year (UMI1 and UST1). This research investigates the following hypothesis: UMI1/UST1 can predict AINF (with an accuracy of >60%) using historical financial indices of: 30-year fixed rate mortgage average, National Home Price Index, Oil Price, unemployment rate, and money supply growth. Collected data [1990-01-01 to 2022-03-01] partially coincided with the Great Recession and the COVID-19 pandemic. To isolate the affected data, five partitions of Calm1, Chaos1, Calm2, Chaos2, and ALL were created. The first and second pairs contain data for the period “before” and “during” the two events, respectively, and the last partition contains all data. Each partition has UMI1 and UST1 versions. The greedy-reduct for each of the ten training sets was identified. Rules were extracted from the reducts using Rough Sets (RS), Association Analysis (AA), and Learning by Example (LE) approaches. The application of the generalized rules on corresponding test sets reveals that AA and RS rules delivered the worst and best performances with six and zero hypothesis rejections, respectively.
KW - Financial Indices
KW - Greedy Reducts
KW - Inflation Expectation
UR - https://www.scopus.com/pages/publications/105014339505
U2 - 10.1007/978-3-031-94953-1_5
DO - 10.1007/978-3-031-94953-1_5
M3 - Conference article
AN - SCOPUS:105014339505
SN - 9783031949524
T3 - Communications in Computer and Information Science
SP - 53
EP - 66
BT - Communications in Computer and Information Science
A2 - Arabnia, Hamid R.
A2 - Deligiannidis, Leonidas
A2 - Shenavarmasouleh, Farzan
A2 - Amirian, Soheyla
A2 - Ghareh Mohammadi, Farid
PB - Springer Science and Business Media Deutschland GmbH
T2 - 11th International Conference on Computational Science and Computational Intelligence, CSCI 2024
Y2 - 11 December 2024 through 13 December 2024
ER -
