In a Time Series Problem, is it possible to forecast quantities by learning the patterns of other items? What are my options?
Suppose I own a store that sells a variety of apples and I have the following stats each month.
- Report Date
- Type of Apple (TA)
- Quantity Available(QA)
- Quantity Sold in the Past 30 days(QS30)
- Quantity Shipping In (QSI)
- Quantity Needed to Order(QN)
Lets make the following assumptions/givens:
There are three types of apples: red apples, green apples and yellow apples.
T(1) denotes the first month and T(60) denotes the 60th month.
QA @ T(i + 1) = QA@T(i) + QSI@T(i) - QS30@T(i+1)
I can provide all the data from T1-60 for each apple.
I can also provide all the data for T61 besides QN for each apple.
My goal is predict QN at T61, or the 61st month for each apple.
If I am only concerned about Red Apples, I can just use ARIMAX with data pertaining to only red apples or VAR right?
But what if I suddenly introduce a new apple type such as orange apples and only have a history from T1-4?
Given I need to use T1-4 for the orange apples... Is it possible to use other data from the red, green and yellow to aid in properly calculating a QN value for orange apples at T5?
Topic deep-learning time-series python r machine-learning
Category Data Science