Risk analysis in time series forecasting (42 minutes)

Data analytics and forecasting represents a strategic competence in organizations these days. The data analytics revolution has made an enormous mass of data available, and this is transforming business decisions. The accuracy of forecasts defines the success or failure of planning decisions on aspects so diverse as production volumes, credit to customers, inventory levels or the amount of insurance to buy.

Despite the data revolution, every forecast still has risk attached to it. As N.N. Taleb wrote in Fooled by Randomness: "Professionals forget the following reality. It is not the estimate or the forecast that matters so much as the degree of confidence with the opinion….We can see that my activity in the market depends far less on where I think the market is going so much as it does on the degree of error I allow around such a confidence level."

Therefore, in this session we will discuss how to properly forecast variables with time series models (using ModelRisk), how to present the forecasts and how to incorporate the forecasted stochastic processes in financial models.