I am a retailer trying to forecast sales for each product.
The events that have the most impact on the retailer are neighborhood events and having a sale in store.
Amazon forcast's Related Time Series Dataset allows us to use promotions per product, such as item_id, timestamp, promotion_applied, but it is difficult to send information for all products in this format.
Amazon forcast has built-in holiday data, but can we use our own store-wide or regional event information in addition to this data?
For example, information such as
2021-8-14, have a summer sale [begin]
2021-8-15, have a summer sale
2021-8-16, have a summer sale
2021-8-16, local festival
2021-8-17, have a summer sale [end]
2021-9-4, local festival
2021-9-24, before school holiday
2021-9-25, school holiday
*Aug-16 has two events on the same day.
If I can have this kind of setup, is it better to specify the beginning and end of the sale? like [begin] or [end].
Generally, sales tend to be larger on the start and end dates of a sale.
Also, if sales are slightly higher on the day before a school holiday, would it be better to include information such as before school holiday?
Related
If someone could please advise on how to achieve the following function on my site: I have a business where I ship live animals to customers. The challenge is communicating the weather forecast with the customer, along with the safest day/s to ship for the animals’ wellbeing. This planning is especially key during the peak summer and winter months when temperatures are very extreme. I am looking to automate these functions during the customers checkout process, giving them control of the shipping date. I am looking to implement something like this on my site.
I found another website where I recently placed an order that provided this relevant information for the customer to review before deciding on what day they would like to have the animal shipment shipped out. The table provided a 5 day forecast, which included temperatures for morning and evening at the point of origin, in transit, as well as the customers’ destination address. Any day/s where the temperature is too hot or too cold was marked as unavailable (red) for shipping. Possible shipping dates consisted of two consecutive days where temps are in the safe range and labeled as available (green) Excluding Friday, Saturday, and Sunday. It is also important for the customer to plan ahead and pick a shipping day based on their availability to be home to receive the package the following morning.
I'm trying to predict (based on simple average) energy consumption untill the end of the month.
I have a table with accumulated energy consumption of my plant until yesterday.
Data Structure in Power Query
'Energy Meter Code', 'Date', 'Hour of the Day', 'Day of the week = Dia Semana', and 'Consumption (MWh)' are the most important columns in this table.
I understand my next step is to:
Create a table with the rest of the days of current month
Calculate average consumption based on different parameters (day of the week, hour of the day, etc) for each hour of the following days
Merge two tables and it's done
However, I don't know how to customize tables in Power Query (syntax problem).
Is there any simple way where I may create dynamic table considering the missing days till the end of the month? Or even better, considering how many hours do we have
Thanks in advance for sharing your experience
I need to build a student cohort tracking pbix so as to show students who have progressed onto the next consecutive year, students who have continued their studies and other similar metrics. Currently, I have a standard star schema as follows:
Fact Enrolment – Logs all enrolment activity for each student (multiple records can exist in the fact for each student based on different years, statuses, courses etc)
Student – Shows all students and their personal details such as email addresses, phone numbers etc. I’d rather not build upon this table as it is quite large as it currently stands.
Year of Study - This table helps to identify which year a student is studying in (e.g second year)
University Academic Year – This lists all academic years (e.g. 2017/18)
Student Status Per Year - This table lists all the possible statuses a student can have for a particular year of their degree such as ‘Current Student’, ‘withdrawn’, ‘transferred’
I was thinking of building a dimension in Power Query which shows cohort tracking for each student and links back to the fact in the standard one-to-many relationship. This will enable end-users to slice the data further by faculty etc. However, I’m not entirely sure how to do this. I was thinking of using Cohort Analysis but this does not appear to do what I need it to.
Any advice would be much appreciated.
i have created a model in AWS
contains Sales records by date
for example
Type: Sale,Time:2016-08-01,Success:1 (1 is a boolean)
i want to predict how much Sales will be after 1 month from the latest date (2016-08-01)
which means a combo of Type=Sale AND Time >2016-08-01 and Success=1
any idea how to achieve this
thank u
You need to aggregate your data to a wider array of attributes to be able to use Amazon ML for such predictions. You can use different level of aggregation, for example daily, weekly and monthly.
You should also add any relevant information for the items that you are selling. For example, if you are selling umbrellas, you should add information about the amount of rain on that day, or if you are selling flowers, you should add information about day of the week or proximity to holidays, when people are buying more flowers.
http://msdn.microsoft.com/en-us/library/windows/apps/hh694058.aspx
"Microsoft will pay you an amount equal to the Net Receipts for your
app, minus the Store Fee (the “App Proceeds”) as full compensation for
your app as made available to customers from the Windows Store, on a
monthly basis"
Please specify what the current practical behavior of "on a monthly basis" means. Eg, what is the current implemented payment schedule.
In the instance that Microsoft employees read this, please consider amending the public agreement to specify the expected behavior, eg similar to the Facebook agreement:
Microsoft will make payment of your Developer Balance approximately X number of days following the end of the Timespan period in which the transaction occurred, except as otherwise set forth herein.
Where X is the expected number of days after the particlar Timespan that transactions are grouped into. Eg, X is 2, and Timespan is monthly.
First of all, Microsoft will not pay anything less than a $200(USD) check, so you must clear that hurdle first. Once you trigger over $200 a month steadily, you will get paid regularly on a monthly basis.
Also note that your cut is only 70% of the first $25,000 USD and then 80% on anything after.
As a developer, I do not make the $200 in a month, but it is generally only a day or two after I notice that I have hit the $200 threshold until my bank account gets creditted with the balance.