US2018101876A1PendingUtilityA1
System and method for determining retail-business-rule coefficients from current prices
Est. expiryJun 5, 2032(~5.9 yrs left)· nominal 20-yr term from priority
G06Q 30/0283
64
PatentIndex Score
0
Cited by
0
References
0
Claims
Abstract
Business rules can govern a single price or they can define relationships between different products involving two or more decision prices. One problem that retailers can face is that business rules are generally not codified and are rarely followed consistently, and thus it can be difficult to articulate existing business rules or generate new business rules. However, existing price information inherently contains industry knowledge and experience, even if retailers find it difficult to express that knowledge. The disclosed technology generates business rules by reverse engineering rule bounds and coefficients from existing price information. The reverse engineered rule bounds and coefficients can be used in price optimization to generate recommended prices for retail products that optimize revenue and profit while complying with a set of business rules.
Claims
exact text as granted — not AI-modified1 . (canceled)
2 . A computer-implemented method comprising:
receiving at least one data file comprising sales data for at least one product, in at least one store, across a plurality of time periods, wherein the sales data includes at least one time period with zero unit sales; and calculating, via a processor, a plurality of coefficients for a demand model for product-store combinations based on the at least one data file as follows:
computing a derivative vector D and a Hessian matrix H by applying a truncated Poisson distribution to non-zero unit sales in the at least one data file; and
computing a coefficient vector V via a Newton-Raphson method using the derivative vector D and the Hessian matrix H, wherein the coefficient vector V comprises the plurality of coefficients, and wherein the plurality of coefficient include coefficients for elasticity and quantity factors for the product-store combinations;
generating the demand model based on the plurality of coefficients; and determining, from the demand model, quantities for the at least one product in the at least one store to prevent an out-of-stock event.
3 . The computer-implemented method of claim 2 , further comprising repeating the calculating until a termination criteria for the coefficient vector V is met.
4 . The computer-implemented method of claim 2 , wherein applying the truncated Poisson distribution to the sales data comprises:
for each product-store combination K and time period T computing a forecast F KT ; and computing derivatives for elasticity β and product-store combinations for derivative vector D.
5 . The computer-implemented method of claim 2 , wherein the computing of the derivative vector D comprises:
computing a derivative D β for elasticity β and a derivative D q k for each product-store combination K, wherein
D
β
=
∑
KT
P
KT
F
KT
-
P
KT
U
KT
+
P
KT
E
KT
,
and
D
q
K
=
∑
T
-
F
KT
+
U
KT
-
E
KT
,
where U KT is units sold for price-store combination K in time period T at the price P KT , and E KT =C KT A KT F KT , A KT =e −F KT ,
C
KT
=
1
1
-
A
KT
.
6 . The computer-implemented method of claim 2 , wherein the computing of the Hessian matrix H comprises:
computing
H
ββ
=
∑
KT
-
P
KT
2
F
KT
-
P
KT
2
G
KT
F
KT
;
computing
H
β
q
K
=
H
q
K
β
=
∑
T
P
KT
F
KT
+
P
KT
G
KT
F
KT
;
and
computing
H
q
K
q
K
=
∑
T
-
F
KT
-
G
KT
F
KT
,
where U KT is units sold for price-store combination K in time period T at the price P KT , and G KT =−C KT 2 A KT 2 F KT −C KT A KT F KT +C KT A KT , A KT =e −F KT , and
C
KT
=
1
1
-
A
KT
.
7 . The computer-implemented method of claim 2 , wherein applying a Newton-Raphson method using the derivative vector D and Hessian matrix H comprises:
computing W=V−H −1 D; and copying W into V when ∥V−W∥>=ε.
8 . The computer-implemented method of claim 2 , further comprising:
obtaining an initial coefficient vector V comprising coefficients for elasticity β and quantity factors for product-store combinations based on sales history weighted against an assumption that average prices chosen in the sales history are optimal for demand; and repeating the calculating until a termination criteria for the coefficient vector V is met.
9 . A manufacture comprising:
a non-transitory computer-readable storage medium; and a computer executable instruction stored on the non-transitory computer-readable storage medium which, when executed by a computing device, causes the computing device to perform a method comprising:
receiving at least one data file comprising sales data for at least one product, in at least one store, over a plurality of time periods, wherein the sales data includes at least one time period with zero unit sales; and
calculating a plurality of coefficients for a demand model for product-store combinations based at least on the at least one data file by iteratively applying:
a truncated Poisson distribution to non-zero unit sales in the sales data to compute a derivative vector D and a Hessian matrix H, and
a Newton-Raphson method using the derivative vector D and the Hessian matrix H to compute an updated coefficient vector V, the coefficient vector V comprising the plurality coefficients
generating the demand model based on the plurality of coefficients; and
determining, from the demand model, quantities for the at least one product in the at least one store to prevent an out-of-stock event.
10 . The manufacture of claim 9 , wherein iteratively applying a truncated Poisson distribution and a Newton-Raphson method comprises:
initializing the coefficient vector V; iteratively updating the coefficient vector V by performing a number of rounds, the number of rounds determined dynamically based on a change in the coefficient vector V, each round comprising:
for each product-store combination K and time period T represented in the at least one data file with known unit sales, computing a forecast F KT ,
computing for derivative vector D, a derivative D β for elasticity β and a derivative D q k for each product-store combination K, wherein
D
β
=
∑
KT
P
KT
F
KT
-
P
KT
U
KT
+
P
KT
E
KT
,
and
D
q
K
=
∑
T
-
F
KT
+
U
KT
-
E
KT
,
where U KT is units sold for price-store combination K in time period T at the price P KT , and E KT =C KT A KT F KT , A KT =e −F KT ,
C
KT
=
1
1
-
A
KT
;
generating a Hessian matrix H, wherein
H
ββ
=
∑
KT
-
P
KT
2
F
KT
-
P
KT
2
G
KT
F
KT
,
H
β
q
K
=
H
q
K
β
=
∑
T
P
KT
F
KT
+
P
KT
G
KT
F
KT
,
and
H
q
K
q
K
=
∑
T
-
F
KT
-
G
KT
F
KT
,
where
G KT =C KT 2 A KT 2 F KT −C KT A KT F KT +C KT A KT ;
computing a new coefficient vector W such that W=V−H −1 D; and
computing a difference between W and V, and copying W into V when the difference is greater than a predefined value ε.
11 . The manufacture of claim 10 , wherein initializing the coefficient vector V comprises reverse engineering coefficients for elasticity β and quantity factors for product-store combinations based on sales history weighted against an assumption that average prices chosen in the sales history are optimal for demand.
12 . The manufacture of claim 9 , wherein a product-store combination K comprises a collection of products in a price family and a set of stores in a zone.
13 . The manufacture of claim 9 , wherein the sales data includes inventory data.
14 . The manufacture of claim 9 , wherein the demand model is used for at least one of price optimization, promotion optimization, markdown optimization, assortment optimization, shelf-space optimization, or retail replenishment.
15 . The manufacture of claim 9 , wherein the plurality of coefficients in the coefficient vector V comprise coefficients for elasticity β and quantity factors for product-store combinations.
16 . The manufacture of claim 9 , wherein the plurality of coefficients in the coefficient vector V comprises coefficient for at least one of price, promotional status, seasonality, holidays, trends, or external factors.
17 . A system comprising:
a processor; a computer readable storage medium storing instructions for controlling the processor to perform steps comprising:
receiving at least one data file comprising sales data for at least one product, in at least one store, across a plurality of time periods, wherein the sales data includes at least one time period with unknown unit sales; and
calculating a plurality of coefficients for a demand model for product-store combinations based at least on the at least one data file as follows:
iteratively updating a coefficient vector V comprising the plurality coefficients by performing a number of rounds, the number of rounds determined dynamically based on a change in the coefficient vector V, each round comprising:
for each product-store combination K and time period T represented in the sales data with non-zero unit sales, applying a truncated Poisson distribution to the non-zero unit sales data to compute a derivative vector D and a Hessian matrix H;
applying a Newton-Raphson method using the derivative vector D, the Hessian matrix H, and a current coefficient vector V to compute a new coefficient vector W; and
computing a difference between W and V, and copying W into V when the difference is greater than a predefined value epsilon;
generating the demand model based on the plurality of coefficients; and
determining, from the demand model, quantities for the at least one product in the at least one store to prevent an out-of-stock event.
18 . The system of claim 17 , wherein applying a Newton-Raphson method using the derivative vector D, the Hessian matrix H, and the coefficient vector V comprises:
computing W=V−H −1 D.
19 . The system of claim 17 , wherein the plurality of coefficients in the coefficient vector V comprise coefficients for at least one of elasticity, quantity, price, promotional status, seasonality, holidays, trends, or external factors.
20 . The system of claim 17 , wherein the sales data includes inventory data.
21 . The system of claim 17 , wherein the demand model is used for at least one of price optimization, promotion optimization, markdown optimization, assortment optimization, shelf-space optimization, or retail replenishment.Cited by (0)
No later patents cite this yet.
References (0)
No backward citations on record.