Volatility Modelling

Volatility work you can defend: clean realised measures, an arbitrage-free implied surface, term structure and skew tracked over time, and forecasts compared on loss functions chosen before the test.

Free · Mac (Apple silicon) and Windows · v1.0.5 · Other platforms

Then open the Marketplace in the app, search for Volatility Modelling, and click Install. It goes into your own files, and works offline from then on.

Before you start: this plan is general information to help you organise decisions about money. It is not financial, investment, tax or legal advice, and it does not recommend any product, investment or deal. Rules differ between countries, so check decisions that matter with a qualified, licensed adviser in yours. Investing and trading can lose money, and raising or managing other people's money is regulated in most countries.

What it installs.

1

Pillar

1

Area

50

Projects

200

Starter tasks

🧮 Quantitative Finance & Trading

Volatility Modelling

Modelling and forecasting volatility: realised measures, implied volatility surfaces, term structure, skew and comparing forecasts honestly.

  1. Map of where volatility numbers drive decisions
  2. House conventions for volatility units and annualisation
  3. Clean daily price history for volatility estimates
  4. Close-to-close realised volatility baseline
  5. Intraday sampling frequency for realised variance
  6. Implied volatility extraction pipeline from option quotes
  7. Forwards, dividends and rates inputs for implied volatility
  8. Forecast evaluation rules fixed before testing
  9. Benchmark volatility forecasts every model must beat
  10. Volatility model documentation file
  11. Daily implied volatility surface checks
  12. Weekly realised against implied volatility monitor
  13. Monthly volatility forecast scorecard
  14. Monthly arbitrage audit of the fitted surface
  15. Weekly term structure and skew snapshot log
  16. Scheduled event calendar for volatility forecasts
  17. Quarterly re-estimation and parameter stability review
  18. Annual volatility model review
  19. Volatility data exceptions queue
  20. Range-based volatility estimators compared
  21. Microstructure noise and realised kernel study
  22. Jumps and bipower variation in realised measures
  23. Implied volatility inversion from first principles
  24. Model-free implied variance and a VIX-style index
  25. Smile dynamics under sticky strike and sticky delta
  26. Reading list for volatility modelling
  27. Asymmetric volatility response to falling prices
  28. SVI parametrisation of each expiry's smile
  29. Surface-wide parametrisation choice
  30. Wing extrapolation rule for illiquid strikes
  31. EWMA decay choice tested out of sample
  32. Blending implied and realised volatility forecasts
  33. Overnight and weekend variance treatment
  34. Vendor surface against in-house fit comparison
  35. Forecast horizon matched to each decision
  36. Earnings season implied move study
  37. Central bank meeting volatility study
  38. Volatility model go-live with a parallel run
  39. Forecast comparison presented at the research meeting
  40. Post-mortem of a volatility spike the model missed
  41. First 90 days as a volatility researcher on an options desk
  42. Volatility research on a solo researcher's budget
  43. From econometrics PhD to volatility research
  44. Volatility forecasting showcase for a portfolio
  45. Volatility model handover to independent validation
  46. Volatility targeting overlay research with written risk rules
  47. Rough volatility study
  48. Local volatility extraction from the fitted surface
  49. Implied correlation from index and constituent options
  50. Regime-switching volatility forecasts

Where it starts.

Each project arrives with its purpose, milestones and first tasks written out. Here is how the first three read.

Map of where volatility numbers drive decisions

Estimates of volatility leak into far more places than the model owner knows: option marks, risk limits, position sizes, margin estimates and client reports. Listing each use with its horizon and the person who reads it shows which forecast needs to be good at one day, which at three months, and where a single number is being stretched to serve both.

First tasks

  • Collect last month's reports and screens that show a volatility figure
  • List each figure with its source and the person who reads it
  • Ask three readers which decision each figure changes for them
  • Flag every figure used at a horizon its model was not built for

House conventions for volatility units and annualisation

Half the arguments about whether a forecast was right are really about units: log or simple returns, 252 or 365 days, calendar or business time, variance or volatility, percent or decimal. Writing one conventions sheet before building anything stops a model from being judged against a benchmark quoted on a different basis.

First tasks

  • Write down the return type and annualisation factor you use today
  • Check which day-count basis each data source quotes in
  • Draft the conversion rules between variance and volatility
  • Link the sheet from the top of every volatility notebook

Clean daily price history for volatility estimates

One unadjusted split or a stale closing print shows up as a huge return, and a squared return magnifies it into a volatility spike that never happened. Building a checked daily open, high, low and close history with corporate actions applied gives every realised estimator a base you can trust.

First tasks

  • Choose the instrument list and history start date for the study
  • Apply split, dividend and roll adjustments and record the method
  • Check the ten largest absolute returns against a second source
  • Flag stale and zero-range days in a separate column

Make it yours.

Install Volatility Modelling, then tell Aurum the date you're aiming for. It checks whether the plan fits the weeks you actually have.

Free · Mac (Apple silicon) and Windows · v1.0.5 · Other platforms

Blueprints are general information to help you organise your own work. They are not medical, financial, legal or other professional advice. See the Terms.