Financial Big Data Solutions for State Space Panel Regression in Interest Rates Dynamics

2018 ◽  
Author(s):  
Dorota Toczydlowska ◽  
Gareth Peters
Keyword(s):  
Big Data ◽  
Interest Rates ◽  
State Space ◽  
Panel Regression

scholarly journals Financial Big Data Solutions for State Space Panel Regression in Interest Rate Dynamics

Econometrics ◽  
2018 ◽  
Vol 6 (3) ◽  
pp. 34
Author(s):  
Dorota Toczydlowska ◽  
Gareth Peters
Keyword(s):  
Big Data ◽  
State Space ◽  
Yield Curve ◽  
State Space Model ◽  
Principal Component ◽  
State Space Models ◽  
Panel Regression ◽  
Stochastic Representation ◽  
Policy Interventions ◽  
Reduction Methods

A novel class of dimension reduction methods is combined with a stochastic multi-factor panel regression-based state-space model in order to model the dynamics of yield curves whilst incorporating regression factors. This is achieved via Probabilistic Principal Component Analysis (PPCA) in which new statistically-robust variants are derived also treating missing data. We embed the rank reduced feature extractions into a stochastic representation for state-space models for yield curve dynamics and compare the results to classical multi-factor dynamic Nelson–Siegel state-space models. This leads to important new representations of yield curve models that can be practically important for addressing questions of financial stress testing and monetary policy interventions, which can incorporate efficiently financial big data. We illustrate our results on various financial and macroeconomic datasets from the Euro Zone and international market.

EDUCATION PREMIUM IN THE ONLINE PEER-TO-PEER LENDING MARKETPLACE: EVIDENCE FROM THE BIG DATA IN CHINA

2018 ◽  
Vol 63 (01) ◽  
pp. 45-64 ◽  
Author(s):  
JUANJUAN CHEN ◽  
YABIN ZHANG ◽  
ZHUJIA YIN
Keyword(s):  
Higher Education ◽  
Big Data ◽  
Interest Rates ◽  
Lower Risk ◽  
Education Level ◽  
Peer To Peer ◽  
Bachelor's Degrees ◽  
P2p Lending ◽  
Peer Lending

We study the education premiums in the online peer-to-peer (P2P) lending marketplace in which individuals bid on unsecured microloans applied by individual borrowers. Using more than 100,000 consummated and failed listings from the largest online P2P lending marketplace in China — Paipaidai.com, we examine whether higher education level lead to lower interest rates and lower risk of default. We find that controlling for other characteristics of borrowers, borrowing rates of borrowers with bachelor’s degrees is 0.141 percent higher than that of borrowers with associate’s degrees, and that female borrowers’ education premiums were higher than their male counterparts. With regard to loan performance, borrowers with bachelor’s degrees are 13% less likely to default than the borrowers with associate’s degrees. Therefore, the education premiums in the P2P lending marketplace are rational.

scholarly journals Default and determinacy under quantitative easing

2021 ◽  
Author(s):  
Nikolaos Romanidis ◽  
Dimitrios P. Tsomocos
Keyword(s):  
Interest Rates ◽  
State Space ◽  
Quantitative Easing ◽  
Defaultable Bond ◽  
Full State ◽  
States Of Nature

AbstractWe show that the path of inflation under quantitative easing policies that target interest rates, is determinate in the presence of default. We achieve this through different payoff profiles that a collateralised defaultable bond achieves in different states of nature with distinct default outcomes. In the model, heterogeneous households trade this bond and other shorter maturity risk-free bonds to maximize their intertemporal utility of consumption and labour. The differentiated payoffs of the collateralised bond, in an equilibrium with active default, span the full state space giving determinacy of prices and inflation as an outcome. This, implies that quantitative easing as implemented by the ECB in the recent years, can control the stochastic path of inflation.

scholarly journals An Unconventional Example of Big Data: BIST-100 Banking Sub-Index of Turkey

2018 ◽  
Author(s):  
Sadullah Çelik ◽  
Elif İşbilen
Keyword(s):  
Big Data ◽  
Stock Market ◽  
Interest Rates ◽  
Stock Exchange ◽  
Great Influence ◽  
Wavelet Coherence ◽  
Exchange Market ◽  
Economic Agents ◽  
Turkish Economy ◽  
Rich Data

This paper applies Big Data concept to an emerging economy stock exchange market by examining the relationship between price and volume of the Banking index in BIST-100. Stock markets have been commonly analyzed in big data studies as they are one of the main sources of rich data with recordings of hourly and minutely transactions. In this sense, nowcasting the economic outlook has been related to the fluctuations in the stock exchange market as news from companies open to public became important sources of changes in expectations for economic agents. However, most of the previous studies concentrated on the main stock market indices rather than the major sub-indices. This study covers the period 13 December 2017 – 12 March 2018, with minute data and approximately 31000 observations for each of the 11 bank stocks. The effects of stock market movements on exchange rates and interest rates are also examined. The methodologies used are frequency domain Granger causality of Breitung and Candelon (2006) and wavelet coherence of Grinsted et al. (2004). The main finding is the supremacy of the banking index as it seems to have great influence on economic fluctuations in Turkish economy through other high frequency variables and the households’ expectations.

Estimating and Forecasting a Term Structure of Interest Rates with State-Space Nelson-Siegel Model

2011 ◽  
Vol 19 (3) ◽  
pp. 309-334
Author(s):  
Joonhyuk Song
Keyword(s):  
Random Walk ◽  
Interest Rates ◽  
State Space ◽  
Term Structure ◽  
Yield Curve ◽  
Predictive Ability ◽  
Predictive Performance ◽  
The State ◽  
Space Representation ◽  
Forecast Horizon

This paper estimates a Nelson-Siegel model under the state-space representation in order to circumvent the shortcomings of the conventional Nelson-Siegel model and evaluates the predictive ability of the estimated model. The results indicate that the estimated Nelson-Siegel time-varying three factors have close relations to their counterparts : level, slope and curvature and the inflection of the Korean yield curve is located around the maturity of 55-month. Meanwhile, each factor is found to have unit-root but differenced-factors do not show signs of unit-roots, hence proved I (1) series. In order to assess the efficacy of the estimated model, we compare the yield prediction from our model with several natural competitors : random walk, Fama-Bliss, and Cochrane-Piazzesi. With respect to out-of-sample performance, Fama-Bliss model proves to be the worst in term structure forecasts in Korea. The predictive performance differs between the random walk and the state-space Nelson-Siegel model depending on the forecast horizon lengths. At the shorter horizon, the state-space Nelson-Siegel model outperforms the random walk, but the table is turned in the longer horizon

Sign in / Sign up

Export Citation Format

Share Document