Product-family inventory replenishment system using a composite product mix framework
In accordance with embodiments of the present disclosure, systems and methods for inventory replenishment utilize supply chain data comprising a demand mix, an inventory mix, and a composite product mix to generate a new composite product mix for at least one future period. The system geometrically discounts demand-inventory composite data. Thus, the older data carries less weight in determination of the new composite product mix percentage. Smoothing factors allow the discounting to be applied differently to demand and inventory data. The new composite product mix and an estimate of the total target replenishment quantity of a product family are used to estimate individual target replenishment quantities for each of a plurality of individual products in a product family. Replenishment quantities can be determined for an extended planning horizon. A server may provide the replenishment quantities to the user of a client computer over a computer network.
1. A system for forecasting the future supply chain needs of a plurality of individual products within a product family, the system comprising:
a data storage device storing at least a current composite product mix, wherein the current composite product mix comprises percentages for the plurality of individual products within the product family;
a computer processor configured to:
receive a first parameter a and a second parameter β for the product family,
receive the current composite product mix P k,t for product k at a time t, a current demand mix D k,t for product k at time t, and a current inventory mix I k,t for product k at time t, the mixes being associated with the product family, and
generate a new composite product mix P k,t+1 for product k at time t+1 according to:
P k,t+1 =β(α D k,t +(1−α) I k,t )+(1−β) P k,t , wherein:
β represents a weighting smoothing factor which is a real number equal to or between 0 and 1 indicating a level of weight to be applied to the current demand mix and the current inventory mix;
α represents a confidence smoothing factor which is a real number equal to or between 0 and 1 indicating a confidence level in the current demand mix or the current inventory mix; and
a display in connection with the computer processor for communicating the new composite product mix.
2. The system of claim 1 , wherein the computer processor is configured to receive data from at least one data storage device accessed via a computer network, the data comprising at least one of the first parameter, the second parameter, the current demand mix, the current inventory mix, and the current composite product mix.
3. The system of claim 1 , wherein the computer processor is a server, the server is further configured to retrieve from a database at least one of the current demand mix, the current inventory mix, and the current composite product mix and communicate the new composite product mix to a client computer.
4. The system of claim 3 , wherein retrieving from the database at least one of the current demand mix, the current inventory mix, and the current composite product mix comprises:
retrieve inventory data and demand data from at least one operational period;
generating at least one demand mix and at least one inventory mix; and
generating the new composite product mix based on the at least one demand mix and the at least one inventory mix, and the current composite product mix.
5. The system of claim 1 , wherein the computer processor is further configured to receive a family target replenishment quantity associated with the product family.
6. The system of claim 5 , wherein the computer processor is further configured to compute a plurality of individual target replenishment quantities for each of the plurality of individual products using the new composite product mix and the family target replenishment quantity.
7. The system of claim 6 , wherein the computer processor is further configured to compute a plurality of individual target replenishment quantities for each of a plurality of future operational periods using the new composite product mix and a plurality of family target replenishment quantities associated with the plurality of future operational periods.
8. The system of claim 1 , wherein the current inventory mix is computed by dividing a plurality of reciprocals of an inventory quantity of each of the plurality of individual products by the sum of the plurality of reciprocals to yield a percentage inventory value for each of the plurality of individual products.
9. The system of claim 1 , wherein the computer processor is further configured to compute an error associated with the new composite product mix.
10. The system of claim 9 , wherein calculating the error associated with the new composite product mix is performed by the computer processor according to:
∑
t
=
-
n
-
1
∑
k
=
1
m
(
u
t
+
1
×
P
k
,
t
+
1
+
r
t
×
I
k
,
t
)
-
(
s
t
+
1
×
D
k
,
t
+
1
)
m
×
n
,
wherein:
u t+1 is a total replenishment quantity associated with the product family at a time t+1;
D k,t is a historical demand mix component for an individual product k at a time t;
r t is a total inventory quantity for the product family at t;
I kt is a historical inventory mix component for k at t;
s t+1 is a total demand quantity for the product family at t+1;
m is a total number of individual products in the product family; and
n is a total number of historical periods for which data is available.
11. A method for creating a new composite product mix of a product family, comprising the steps of:
receiving a first parameter and a second parameter into a data storage device;
receiving a current composite product mix, a current demand mix, and a current inventory mix, the mixes being associated with a plurality of individual products within the product family, into the data storage device;
generating, by use of a computer processor, the new composite product mix associated with the product family according to:
P k,t+1 =β(α D k,t +(1−α) I k,t )+(1−β) P k,t , wherein:
β is the second parameter which represents a smoothing factor which is a real number equal to or between 0 and 1 indicating a level of weight to be applied to the current demand mix and the current inventory mix;
α is the first parameter which represents a smoothing factor which is a real number equal to or between 0 and 1 indicating a confidence level in the current demand mix or the current inventory mix;
D k,t is the current demand mix percentage for an individual product k at a time t;
I k,t is the current inventory mix percentage for k at t;
P k,t+1 is the current composite product mix percentage for k at t; and
P k,t+1 is the new composite product mix percentage for k at t+1;
receiving a total target replenishment quantity for the product family; and
generating a plurality of individual target replenishment quantities for each of the plurality of individual products within the product family based on the new composite product mix and the total target replenishment quantity.
12. The method of claim 11 , further comprising:
determining whether the product family is subject to a replenishment limitation;
receiving a replenishment-limitation value;
computing adjustments to the plurality of individual target replenishment quantities based on the new composite product mix and the replenishment-limitation value; and
generating a plurality of adjusted individual target replenishment quantities.
13. The method of claim 11 , further comprising receiving from a database a set of data comprising historical inventory data and historical demand data.
14. The method of claim 13 , further comprising generating, by use of a computer processor, at least one of the current demand mix, the current inventory mix, and the current product mix from the set of data comprising historical inventory data and historical demand data.
15. The method of claim 11 , further comprising calculating an error value associated with the new composite product mix.
16. The method of claim 11 , further comprising using a plurality of total target replenishment quantities associated with a plurality of future time periods and the new composite product mix to compute a multi-period plurality of individual target replenishment quantities.
17. A non-transitory machine-readable medium comprising a plurality of machine-readable instructions which when executed by one or more processors of a computer are configured to cause the computer to perform a method comprising:
receiving a first parameter and a second parameter;
receiving a current composite product mix for a plurality of individual products within a product family, the current composite product mix containing a plurality of percentage values corresponding to each of the plurality of individual products;
receiving a current demand mix and a current inventory mix wherein the mixes are associated with the product family;
generating a new composite product mix for the plurality of individual products within the product family according to:
P k,t+1 =β(α D k,t +(1−α) I k,t )+(1−β) P k,t , wherein:
β is the second parameter which represents a smoothing factor which is a real number equal to or between 0 and 1 indicating a level of weight to be applied to the current demand mix and the current inventory mix;
α is the first parameter which represents a smoothing factor which is a real number equal to or between 0 and 1 indicating a confidence level in the current demand mix or the current inventory mix;
D k,t is the current demand mix percentage for an individual product k at a time t;
I k,t is the current inventory mix percentage for k at t;
P k,t is the current composite product mix percentage for k at t; and
P k,t+1 is the new composite product mix percentage for k at t+1; and
generating a target replenishment quantity of each of the plurality of individual products using the current composite product mix.