Secure Collaborative Planning,
Forecasting, and Replenishment
Vinayak Deshpande
Krannert School of Management
Purdue University
Collaborators:
Mikhail Atallah, Marina Blanton, Keith Frikken, Jiangtao Li
Computer Sciences, Purdue University
Leroy B.Schwarz
School of Management, Purdue University
Research funded by NSF ITR Grant
1
The Starting Point....
“Information Asymmetry” is one of the
major sources of inefficiency in Managing
Supply Chains
==> Wrong Investment in Capacity
==> Misallocation of Resources
==> “Bullwhip Effect”
==> Reduced Customer Service
==> Unnecessary Additional Costs
2
Supply Chain Management Trends
• Collaboration between supply-chain
partners to improve efficiencies
• Information sharing for collaborative
decision making
• National program sponsored by VICS for
establishing collaboration standards – called
CPFR (Collaborative Planning, Forecasting
and Replenishment)
3
.... but, there are Very Good Reasons
for Keeping Asymmetric Information
Asymmetric
• Fear that Supply-Chain Partner will Take
Advantage of Private Information
• Fear that Private Information will Leak to a
Competitor
4
As a result…
• Reluctance to share private/proprietary info
– Even when both sides would gain from sharing
• Consequence: Information asymmetry
– Many inefficiencies
5
Obvious Question…
Is it possible to enjoy the benefits
of Information-Sharing without
Disclosing Private Information?
6
The Future
• Online interactions that give the benefits of
sharing, without its drawbacks
– “As if” information sharing had taken place, yet
without revealing one’s private/proprietary data
• Counterpart’s information is often needed
only as partial input for computing a desired
output
• Can two parties compute desired output
without either learning the other’s input?
7
An Example: Vickrey Auction
• Requires computation of the second highest bid
value and identity of highest bidder from all
submitted bids
• Secure Multi-party Computation (SMC)
protocols can
– Compute the second highest bid without revealing
the identity of the second highest bidder
– Identify highest bidder without revealing his bid
– Not reveal bids of any other bidders
8
Secure multiparty computation
Alice
x
•
•
•
•
Bob
y
Alice has private data x,
Bob has private data y,
They want to jointly compute f(x,y),
Only Alice (or Bob, or both) knows the result.
9
Secure multiparty computation (SMC)
Literature
• A decades old area
– Yao, Goldreich, Micali, Wigderson, … (many
others)
– Elegant theory
– General results
• Circuit simulations, use oblivious transfer
– General results typically impractical
• Recently: Protocols for specific problems
– More practical
10
Mechanism Design Literature
• Studies how private information can be elicited
from agents by providing incentives
• Mechanism design problem simplified through
the revelation principle (principal announces a
menu constructed to induce truth telling)
• No future or side consequences of participating
in the mechanism and truthfully revealing
private information
• Assumes that the entity implementing the
mechanism is trustworthy
11
Supply Chain Literature…
• Has quantified the benefit of information
sharing (e.g. Lee, So and Tang; Cachon and
Fisher)
• Has modeled Supply-Chain Collaboration, e.g.
collaborative forecasting (Aviv 2001, 2003)
• Key obstacles: companies unwilling to share
sensitive information, fear of information
leakage
12
We Propose to
marry three distinct disciplines
• Secure Multi-Party Computation from CS
• Mechanism Design from Economics
• Supply-Chain Management from OM
13
Our Goal..
...we are developing protocols to
enable Supply-Chain Partners to
Make Decisions that
Cooperatively Achieve Desired
System Goals without Revealing
Private Information
14
A Supply Chain Problem..
• Collaborative Forecasting and Planning
without revealing private forecast
information
15
Industry Backdrop
• Collaborative Planning, Forecasting, and
Replenishment (CPFR), an initiative of the
Voluntary Intra-Industry Collaboration Society
(VICS)
– buyer and supplier share inventory-status, forecast, and
event-oriented information and collaboratively make
replenishment decisions
– pilot program between Wal-Mart and Warner-Lambert,
called CFAR: (www.cpfr.org)
• Challenges to CPFR
– fear that competitively-sensitive “private information”
will be compromised
– Necessary to protect “sensitive” forecast information
such as sales promotions from “leaking”
16
Business Scenario
• A supply-chain with two players, a supplier selling to
a retailer.
• The retailer and the supplier receive independent
“signals” about future market demand
– e.g., a retailer has private information about “promotions”
that he may be planning to run in the future which can
affect his forecast of demand;
– the supplier can receive signals about overall “market
trends”
• Incorporating these “signals” can improve forecast
accuracy
• But.. “signal” information should be kept private
17
Demand Model
T
T
dt     r     s     t
i 1
r
t ,i
i 1
s
t ,i
• dt – demand in period t (observed by the retailer only)
• t,ir – Retailer’s signal about period t observed in period t-i
(private information to the retailer)
• t,is –Supplier’s signal about period t observed in period t-i
(private information to the supplier)
• , r , s – unknown parameters to be estimated from past
observations
18
Forecasting Process
• In each period t, estimate , r , s by regressing the
observations dt versus the observed signals t,ir and
t,is
• For the forecast horizon (T periods) construct the
forecast using the following equation:
d j    r
T
T
i  j t
i  j t
r
s




 j ,i s  j ,i
j  t  1,..., t  T
19
Collaborative Inventory Planning
Policy
20
Secure Protocols Example:
Average Salary
21
Secure Protocols Building Blocks:
• Hiding numbers by additively splitting values
-x= xs + xr, Supplier has xs, while retailer has xr
- Modular arithmetic (xs+xr) mod N =x hides x in a
information theoretic sense
Secure addition and subtraction
 Homomorphic Encryption ( E(X) E(Y)=E(X+Y) )
 Secure Split Multiplication
 Secure Split Division
 Secure Scalar Product
 Secure Matrix Multiplication
22
Advanced Building Blocks:
• Secure Matrix Inversion
-Matrix A is split such that As+Ar = A.
- Output supplier learns Bs, retailer learns Br; Bs+Br = B
• Secure Binary Search
• Secure Comparison
-Supplier has X, Retailer has Y,
- Output reveals if X<Y, without revealing X to retailer and Y
to supplier
23
Secure Multiple Linear Regression
Protocol
24
Secure Process for Forecasting and Inventory Planning
25
Step 1: Input cost parameters
Retailer
Supplier
hR  1
hS  0.5
pR  19
pS  15
26
Step 2: Input demand and inventory information
Retailer
Supplier
dt  16.80
tR1,1  0.83
R
t 2,2  0.58
  1.84

 0.81
tS3,3  0.69
tS4,4  0.18

R
t 3,3
 0.88
tR4,4  0.29
OH  7
R
t
BO  0
ITt  22
R
t
R
S
t 1,1
S
t  2,2
OH tS  13
BOtS  0
ITt  19
S
27
Step 2(con’t): Regression
Retailer
Supplier
Supplier
ˆ  14.997
R
ˆ
  0.996
S
ˆ
  0.996
28
Step 3: Leadtime demand forecast
Retailer
Supplier
Overall
t ,[t ,t  L ]  47.46
R
 t ,[ t ,t  L ]  5.02
S
t ,[t ,t  L
R  LS
 t ,[t  L
R  LS
]
 79.35
]
 8.28
29
Step 4: Determine base-stock levels
Retailer
Supplier
Overall
y R*  57.30
y S *  67
30
Step 5: Determine order quantities
Retailer
qtR  28.30
qtS  44
Supplier
qtR  28.30
q  44
S
t
31
Protocol Implementation Issues:
Protocols are verifiable
• The Logic of the Protocol is Auditable
– Logic of Source Code Can be Audited
• Outputs Can be Tested
– Outputs Can be Verified Given Known Inputs
32
Protocol Implementation Issues:
Other Advantages
• Valuable even in Trusted e.g. (intracorporate) interactions
– “Defense in depth” !
– Systems are hacked into, break-ins occur,
viruses occur, spy-ware, bad insiders, etc
– Liability Decreased
• “Don’t send me your data even if you trust me”
• Impact on Litigation and Insurance Rates
33
We Have Only Just Begun...
• Tough Issues to Deal with:
– SMC Complexities; e.g.,
• How to Deal with Collusion
• Computational Complexity (e.g., simultaneity)
– Supply-Chain Modeling Complexities; e.g.
• Contracting/Incentive Issues
– SSCC Complexities; e.g.,
• Inverse Optimization
• Bob’s Objective is fB(xA, xB); Alice’s is fA((xA, xB)
34
Future Work
• Protocols for other supply-chain
applications
– Price-Masking
– Bullwhip Scenarios
– Capacity Allocation
• Protocol implementation issues
– Collusion by a subset of parties
– Intrusion detection
– Incentive issues and mechanism design
35
Questions?...
36
Secure Regression
37
Secure 3x3 Matrix Inverse Protocol
38
Secure Demand Forecasting Protocol
Input: The supplier knows the j,is and the retailer knows the j,ir , for
all j, i such that j = t + 1, ..., t + T and i = j − t, ..., T. The
parameters , r , s are available in additively split form.
Output: Both supplier and retailer learn the forecast dj for all j = t +
1, ..., t + T.
Protocol Steps:
1. For each j  {t + 1, ..., t + T}, the supplier computes vjs = T j,is.
This is a “local” computation, as the supplier has all the j,is values.
The retailer similarly computes vjr = T j,ir for all j  {t + 1, ..., t
+ T}.
2. For each j  {t + 1, ..., t + T}, the supplier and retailer run a split
multiplication protocol twice, once to compute wrj = rvrj and once
to compute wsj = svsj (both in split fashion).
3. For each j  {t + 1, ..., t + T}, the supplier and retailer run a split
addition protocol to compute µ+ wrj+ wsj, which is equal to dj 39.
They exchange their shares of each dj so they both learn its value.