Anticipatory Shipping - Predictive Analytics

Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 11

Anticipatory Shipping

using Predictive
Analytics

What is Predictive Analytics?


Predictive analytics is a branch of advanced analytics that is
an assortment of statistical and mathematical techniques
used to predict the probability of future events occurring.
Predictive analytics uses many techniques from data mining,
statistics, modeling, machine learning, and artificial intelligence
to analyze current data to make predictions about future.
The term Predictive analytics
is generally used to mean
predictive modeling and forecasting.
Increasingly being used to refer to analytical disciplines such as
descriptive modelling, decision modelling or optimization.

History
In the mid-1990s, Stanford University Professor Hau Lee,
founded a company called Non-Stop Logistics
Non-Stop's concept was to forecast, for example a week's
inventory needs for a series of SKUs in a given metro market.
Manufacturers would then ship to that forecast, and a Non-Stop
cross-dock center would fulfill to individual stores based on later
stage insight into inventory levels and demand.
The idea was that aggregate forecasts for a market would always
be more accurate than the specific forecasts for store chains or
individual outlets.
Non-Stop eventually morphed into supply chain planning software
vendor, which was later acquired by Manhattan Associates.

Amazons concept for Speculative Shipping

"In conventional order fulfillment systems, an item is not shipped (or


in many cases even packaged for shipment) until a customer places
an order for that item to be delivered to a specific delivery address.
However, a package including one or more items may be shipped to
a destination geographical area without completely specifying a
delivery address at the time of shipment. Instead, a delivery address
may be completely specified while the package is in transit.
"Such shipment of packages without completely specifying delivery
addresses at the time of shipping may also be generically referred to
as speculative shipping, and completely or partially specifying a
delivery address for a package after that package has shipped may
be generically referred to as late addressing. In such embodiments,
speculative shipping may also be referred to as anticipatory
shipping."

How does Amazon know what you want?


According to the patent, this forecasting model uses data from your
prior Amazon activity, time on site, duration of views, links clicked,
hovered over, shopping cart activity and wish lists.
When possible, the algorithm also sprinkles in real-world
information gleaned from customer telephone inquiries and
responses to marketing materials, among other factors.
Together, this can provide decision support for speculative
shipping of Items, per the patent.
Of course, Amazons algorithms might sometimes err, prompting
costly returns. To minimize those costs, Amazon said it might
consider giving customers discounts, or convert the unwanted
delivery into a gift. Delivering the package to the given customer
as a promotional gift may be used to build goodwill, the patent
said.

References
United States Patent and Trademark Office
Predictive Analytics world
Predictive Analytics future forecast
SC Digest: Not quite as wild as Drone concept, but impres
sive thinking nonetheless
Amazon.com Research and development expense
WSJ: Amazon Wants to Ship Your Package Before You Buy
It
Forbes: Why Amazon's Anticipatory Shipping Is Pure
Genius
Techcrunch: Amazon to
Start Sending Stuff Before Youve Bought It

Thank you!
Questions?

You might also like