Dashboard
Foreign Exchange Risk Classification, made interpretable.
Explore the published 18-currency classification, inspect the reported GARCH(1,1) parameters, examine individual currency profiles, assess investor risk capacity, and analyse new FX datasets directly in the browser.
OPSFXR workflow
Research pipeline represented in the application
Published classification at a glance
Labels are volatility-oriented, not return forecasts
Individual Currency Analysis
Published parameter profile and descriptive exchange-rate-level statistics from the reported sample.
USD / INR
These are descriptive statistics of exchange-rate levels and are not used as directly comparable risk measures across currencies.
GARCH(1,1) profile
How to read this profile
ω is the variance intercept, α captures sensitivity to new shocks, and β captures volatility persistence. The sum α+β is a persistence indicator and should be interpreted cautiously when it is equal or extremely close to one.
Historical chart availability
The manuscript reports static figures but does not embed the underlying 2,255 daily observations in the app. To view genuine price, return and conditional-volatility charts, upload the original CSV/Excel dataset in Analyse New Data.
Reported GARCH(1,1) parameters
ω = variance intercept · α = shock response · β = persistence
| Currency | Omega (ω) | Alpha (α) | Beta (β) | α + β | Persistence note | Published group |
|---|
Persistence check
For a covariance-stationary GARCH(1,1), α + β < 1. Several reported estimates are equal or extremely close to one, so the revised manuscript advises caution and re-estimation with full diagnostic output.
Interpretation boundary
Investor Risk Capacity – Prototype Questionnaire
This questionnaire is an app-design aid, not part of the reported empirical study. It converts simple answers into a prototype risk-capacity score.
Your result
Risk groups within capacity
The manuscript’s suitability rule is conservative: a group is suitable only when its assessed risk does not exceed the investor’s risk capacity.
Analyse a New FX Dataset
CSV and Excel (.xlsx/.xls) are supported. Processing occurs in your browser.
Method represented in the app
Data and returns
Daily INR-based FX observations are aligned and converted to log returns, rₜ = 100 × ln(Pₜ/Pₜ₋₁).
ARCH effects
The dynamic mode provides an ARCH-LM diagnostic before GARCH estimation. The revised study notes that formal ARCH testing is more appropriate than visual inspection alone.
GARCH(1,1)
σ²ₜ = ω + αε²ₜ₋₁ + βσ²ₜ₋₁. The app reports ω, α, β and α+β.
Published fuzzy classification
The original implementation reports a first-stage cutoff of 0.054 and centroid 0.009645. These are retained only for the published classification view.
Dynamic uploaded-data mode
Because full original fuzzy membership definitions and code are unavailable, uploaded-data results use transparent tertiles of estimated conditional volatility and are labelled exploratory.