Exam AWS Certified Machine Learning - Specialty topic 1 question 118 discussion

I would choose A and D, however both of them is not possible at the same time. The question is ambiguous, it could mean which two options, but no necessarily both. A - If you want Amazon Forecast to evaluate each algorithm and choose the one that minimizes the objective function, set PerformAutoML to true. D - The following algorithms support HPO: - > DeepAR+.

It is A and D, there are no weekly data, they have only monthly data and can not switch horizon to 4

A. YES - DeepAR+ most likely to be chosen, but worth a try B. NO - increasing the forecast horizon is not likely to improve the 3 months we want C. NO - we want monthly, nto weekly D. YES E. NO - there are no missing values

The changes to the CreatePredictor API call that could improve the MAPE are option A and option D. By setting PerformAutoML to true, you can enable Amazon Forecast to automatically explore different algorithms and choose the best one for your data and business problem. By setting PerformHPO to true, you can enable Amazon Forecast to perform hyperparameter optimization (HPO) and tune the algorithm parameters to improve the accuracy of the predictor. These options can help you find the optimal configuration for your forecast model without manually specifying the algorithm or the hyperparameters.

A. Set PerformAutoML to true. D. Set PerformHPO to true. Setting PerformAutoML to true will enable Amazon Forecast to automatically select the best algorithm and hyperparameters for your data and problem. This can help improve the MAPE by finding the optimal combination of algorithm and hyperparameters that minimize prediction error. Setting PerformHPO to true will enable Amazon Forecast to perform a hyperparameter optimization search to find the best combination of hyperparameters that result in the best prediction performance. This can help improve the MAPE by finding the optimal combination of hyperparameters that minimize prediction error.

A. Looking for better algorithms performance D. Hyperparameters optimization

12-sep exam

Why are not B and C? The question asks about modifications that increase MAPE (thats bad): B - If FH is larger, error will increase C - Data is based on months, change that will make erros on forecasting values E - There is no data gap so is useless A - Selec best between all should DECREASE MAPE D - Tunning hyperparms will DECREASE MAPE

A&D...>By default, Amazon Forecast uses the 0.1 (P10), 0.5 (P50), and 0.9 (P90) quantiles for hyperparameter tuning during hyperparameter optimization (HPO) and for model selection during AutoML. If you specify custom forecast types when creating a predictor, Forecast uses those forecast types during HPO and AutoML. If custom forecast types are specified, Forecast evaluates metrics at those specified forecast types, and takes the averages of those metrics to determine the optimal outcomes during HPO and AutoML. For both AutoML and HPO, Forecast chooses the option that minimizes the average losses over the forecast types. During HPO, Forecast uses the first backtest window to find the optimal hyperparameter values. During AutoML, Forecast uses the averages across all backtest windows and the optimal hyperparameters values from HPO to find the optimal algorithm.

C. ForecastFrequency M- MONTHLY W- WEEKLY D. PerformHPO Whether to perform hyperparameter optimization (HPO). HPO finds optimal hyperparameter values for your training data. The process of performing HPO is known as running a hyperparameter tuning job. The default value is false. In this case, Amazon Forecast uses default hyperparameter values from the chosen algorithm. E. FeaturizationMethodName The name of the method. The "filling" method is the only supported method.

ABE can be excluded. CD is my answer. A. PerformAutoML If you want Amazon Forecast to evaluate each algorithm and choose the one that minimizes the objective function, set PerformAutoML to true. The objective function is defined as the mean of the weighted losses over the forecast types. By default, these are the p10, p50, and p90 quantile losses. When AutoML is enabled, the following properties are disallowed: AlgorithmArn HPOConfig PerformHPO TrainingParameters B. ForecastHorizon Specifies the number of time-steps that the model is trained to predict. The forecast horizon is also called the prediction length. For example, if you configure a dataset for daily data collection (using the DataFrequency parameter of the CreateDataset operation) and set the forecast horizon to 10, the model returns predictions for 10 days. The maximum forecast horizon is the lesser of 500 time-steps or 1/3 of the TARGET_TIME_SERIES dataset length.