Suppose after you just joined a risk management team, the boss says: Welcome, I have been doing this for twenty years. Here are the volatilities and VaRs I calculated every day. Take a look and see if you can find any problem and make some improvement of the model.

Q: if you found a predictor (or called indicator) that predicts the next day's volatility, You say: that is not supposed to happen, there is something wrong with the volatility model. Boss will say

Question

Suppose after you just joined a risk management team, the boss says: Welcome, I have been doing this for twenty years. Here are the volatilities and VaRs I calculated every day. Take a look and see if you can find any problem and make some improvement of the model.

Q: if you found a predictor (or called indicator) that predicts the next day's volatility, You say: that is not supposed to happen, there is something wrong with the volatility model. Boss will say

BlackTom AI · Accepted Answer

The scenario presents a workplace dialogue in risk management where a junior parses the boss’s readiness to critique the current volatility model after discovering a predictor that forecasts next-day volatility.
Option 1: 'Make sense' — If you told the boss that finding a predictor for next-day volatility makes sense, you’d be implying that the observed forecastability is expected or consistent with the model’s assumptions. However, in a robust risk model, a predictor that reliably predicts next-day volatility often signals a flaw such as data snooping, overfitting, or an issue with the modeling horizon or independence assumptions. Therefore, this option would be inappropriate because the realistic, prudent conclusion is that there is something wrong with the volatility model, not that it makes sense.
Option 2: 'Make no sense' — Saying this indicates that discovering a predictor for next-day volatility is counterintuitive or problematic within the current framework. It suggests that the model might be misspecified, that the predictor is exploiting accidental patterns, or that the model’s structure prohibits predictive signals for near-term volatility. This aligns with common risk-management thinking: a genuine model should not readily yield a dependable next-day volatility predictor without some compensating mechanism or validation; otherwise, it points to data leakage, improper backtesting, or miscalibration. Hence, this choice appropriately signals an issue to investigate.
In short, the 'Make sense' option would falsely reassure about a discovery that typically warrants skepticism and further scrutiny, while 'Make no sense' correctly flags the counterintuitive and potentially problematic nature of a reliable next-day volatility predictor within the described setting.
Additional nuance: when reviewing established models, one would expect volatility to be noisy and difficult to predict deterministically on a day-to-day basis; a consistent predictor would prompt a deeper dive into model assumptions, feature construction, and training/testing protocols to prevent misleading conclusions.

BU.230.730.52.SP25 Final Exam- Requires Respondus LockDown Browser

View Explanation

Log in for full answers

Similar Questions

HAR models the predictive relationship between next day's realized variance and current realized variance. The model equation is:

HAR is a volatility model.

The GARCH model provides a way to predict future return.

HAR is a volatility model.

The GARCH model provides a way to predict future return.

HAR is a volatility model.

I have viewed all of the videos in this course.

More Practical Tools for International Students

Exam Browser Assistant

Stylized Writing Assistant

Plagiarism Checker Assistant

Citation Assistant

In-Class Translation Assistant

Class Notes Assistant

Quiz Search Assistant

Past Exam Questions by School

Smart Practice Assistant

Adaptive Practice

Making Your Study Simpler