Exam AWS Certified Machine Learning - Specialty topic 1 question 191 discussion

I think the answer is BC

BC - https://docs.aws.amazon.com/forecast/latest/dg/aws-forecast-recipe-ets.html

While smoothing can help, it doesn’t directly address the missing data issue or provide the model with additional context about specific sales periods, which are crucial for improving the model’s accuracy around seasonal events

A is for sure. C, watch the keywords mentioned in the question "too low or too high"!

Ans: AC A. Add Information About the Store's Sales Periods: This directly targets the issue of seasonality affecting the sales forecast. C. Apply Smoothing to Correct for Seasonal Variation: Smoothing techniques will help in handling the seasonal trends more effectively, which seems to be a major factor in the model's current performance issues.

both of A and C solves the seasonality issues

A&E for sure. For option E, refer to this blog - https://aws.amazon.com/blogs/machine-learning/prepare-time-series-data-with-amazon-sagemaker-data-wrangler/

A. YES - valuable contextual information B. NO - irrelevant to seasonal events C. YES - Removes noise and can help make patterns easier to identify D. NO - not point to loose precious information such as weekend days E. NO - 5% data loss is not a big deal, might as well drop them

Adding information about the store’s sales periods to the dataset can help the model learn about patterns in sales that are specific to certain times of year. This can help the model make more accurate predictions around seasonal events. ------------------- Smoothing can help correct for seasonal variation by removing some of the noise from the data. This can help the model make more accurate predictions -------------------- None of the other options address the seasonal variation in my opinion

B&C were my top choices without looking at the key.

E for sure then either C or A. would go for A

Answer: AC Smoothing has different uses. Please find the definition Data smoothing can be defined as a statistical approach to eliminating outliers from datasets to make the patterns more noticeable.

ChatGPT say C + E

CE C. Apply smoothing to correct for seasonal variation: Seasonal variation can have a significant impact on sales data. By applying smoothing techniques such as moving averages or exponential smoothing, the ML specialist can reduce the noise and fluctuations caused by seasonal effects, allowing the model to capture the underlying patterns more effectively. E. Replace missing values in the dataset by using linear interpolation: Missing data can introduce biases and affect the accuracy of the model. Linear interpolation is a common technique for filling in missing values by estimating the missing data points based on the available data. By replacing the missing values, the ML specialist ensures that the model has a complete and representative dataset to learn from.

A to improve model in seasonal periods E to fill missing data

I would go for C and E C is quite obvious I think E Linear interpolation is a technique to fill the missing data https://towardsdatascience.com/4-techniques-to-handle-missing-values-in-time-series-data-c3568589b5a8

why not C and D?