FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENTS RULES, 2003
COMPLETE SPECIFICATION (See section 10, rule 13)
1. Title of the invention: SYSTEMS AND METHODS FOR TIRE INVENTORY
MANAGEMENT
2. Applicant(s)
NAME NATIONALITY ADDRESS
CEAT LIMITED Indian RPG House, 463, Dr. Annie Besant Road, Worli, Mumbai- Maharashtra 400030, India
3. Preamble to the description
COMPLETE SPECIFICATION
The following specification particularly describes the invention and the manner in which it
is to be performed.

FIELD OF INVENTION
[0001] The present invention relates generally to inventory management
and more particularly to systems and methods for inventory management for tires.
BACKGROUND
[0002] Tires are among the most important replacement parts of vehicles.
It is expected that the tires would support the weight of a vehicle they are fitted into and the passengers inside, handle daily driving demands in various weather conditions, and last for years after the purchase. The vehicle’s tires also affect braking, make a ride smooth, and play a major role in a vehicle’s performance.
[0003] There may be various categories of tires such as passenger car
tires, truck bus tires, light truck tires, farm use tires, etc. These tires are sold in unique tire sizes that address vehicle specifications. A tire may have a unique combination of load index, rim diameter, speed rating, aspect ratio, section width, and construction type. As a result, a given tire distributor or a dealer may carry a plurality of tire SKU's (stock-keeping units).
BRIEF DESCRIPTION OF THE DRAWINGS
[0004] The following detailed description references the drawings,
wherein:
[0005] Figure 1 illustrates a network environment comprising a system for
providing recommendations on selecting tire stock keeping units (SKUs), in
accordance with an example implementation of the present subject matter;
[0006] Figure 2 illustrates the system for providing recommendations on
selecting the tire SKUs, in accordance with another example
implementation of the present subject matter;
[0007] Figure 3 illustrates a method for providing recommendations on
selecting the tire SKUs within a networked environment, in accordance with
an example implementation of the present subject matter.

[0008] Throughout the drawings, identical reference numbers designate
similar, but not necessarily identical, elements. The figures are not necessarily to scale, and the size of some parts may be exaggerated to more clearly illustrate the example shown. Moreover, the drawings provide examples and/or implementations consistent with the description; however, the description is not limited to the examples and/or implementations provided in the drawings.
DETAILED DESCRIPTION
[0009] In the distribution of a product such as tires, retail distribution may
occur through alternative channels such as multi-category, large regional, car partners, and independent channel partners. Each distributor or dealer within each channel typically develops goals for the tire product category and strategies for achieving such goals. Periodically, the performance of the category may be reviewed by a tire manufacturer to identify high volume, high turn-over tire SKUs (i.e., stock control units), for example, to manage the stock or inventory of tires more efficiently. The review may also be required to determine whether the category has met its intended goals. Should the category fall short, adjustments may be made in the channeling of the tire SKUs in an attempt to correct the category performance.
[0010] The decision for the adjustments into the channeling of the tire
SKUs is conventionally made manually by the tire manufacturers. To make such decisions, the tire manufacturer generally appoints a field representative. Tasks of the field representative, for example, may include helping channel partners to increase tire sales, generate demand reactively, settle channel partner claims, manage their financial transactions, etc. Additionally, the field representative may also be responsible for promoting those lines of tire SKUs to the channel partners which are newly manufactured by the company. For more accurate decisions on the adjustments, these decisions are expected to be based on historic order data associated with the channel partner. However, the historic order data needed for performing such

activities are generally unorganized, due to which the field representative may lack insights into the meaning, or semantic information, of such unorganized data, and thus, he may not be able to retrieve appropriate information from it. Due to a lack of data insights, the field representative may have to rely more on either hunch-based information or market intelligence gained over a period of time for recommending SKUs to the channel partner as identification of an appropriate SKU may not be possible without proper insights on the geographical landscape of the channel partner, SKU order preference of the channel partner, frequency of orders placed by the channel partner and other partners in his vicinity, etc.
[0011] Moreover, the field representatives generally focus on the overall
value being generated and not on the range of SKUs that may be recommended to channel partners for better returns or more efficient inventory management. Even if a field representative does focus on the range of SKUs being delivered, no technique exists to help the field representative identify SKUs, pitching of which to the channel partners would eventually enable him to achieve the desired numbers in range.
[0012] Thus, there exists an urgent need for a technique that may provide
analytics-based actionable insights for the identification of SKUs that may be recommended to the channel partners, for instance, to assist the field representatives to enable SKU-level discussion with the channel partners. At the same time, a technique to calculate the SKUs to be promoted based on the deviation parameter, geography, and the frequency of purchase of the channel partner is also desired.
[0013] Example implementations of a recommendation system for the tire
SKUs are described. The recommendation system may recommend products to the field representative and channel partners so that they may choose the SKUs easily based on the historical order data with the tire manufacturer.
[0014] In an example implementation, the recommendation system for the
tire SKUs comprises a rating generation module. The rating generation

module is configured to determine a first set of SKUs of a category of tires that is frequently ordered by a first channel partner. The category may be passenger car tires, truck bus tires, light truck tires, farm use tires, etc. This determination of the frequently ordered first set of SKUs is made by analyzing historic order data of a predetermined period that is associated with a plurality of channel partners. It is to be understood that in the present context, a channel partner may be a person or a company that partners with a tire manufacturer to market and sells the manufacturer's products, such as tires.
[0015] The historic order data includes a location of each of the plurality
of channel partners and a category of each stock keeping units (SKUs) ordered by each of the plurality of channel partners. It is to be understood that in the present context, the category of the SKUs may correspond to categories of the tires such as small truck tires, heavy-duty tires, and motorcycle tires in addition to passenger car pneumatic tires. The category of the first set of SKUs is from amongst categories of the SKUs ordered by the channel partners from the tire manufacturer.
[0016] The rating generation module, based on the historic order data,
further determines average order of the first set of SKUs placed by the first channel partner with the tire manufacturer over the predetermined period of time. In an example, the order placement may refer to the procedure for a channel partner to purchase the tires. In one example, order placement may be done by selecting the desired SKUs from amongst the list of SKU codes and categories displayed on the server of the tire manufacturer's website. In another example, the order placement may also be done through offline mediums, such as SMS, call, an in-person visit to a retail location of the tire manufacturer, etc.
[0017] Furthermore, the rating generation module determines a deviation
parameter of the first channel partner based on the average order of the first set of SKUs. The deviation parameter indicates deviation or gap in orders of the first set of SKUs by the first channel partner over a period of time. The

rating generation module also determines average order of a second set of SKUs ordered by channel partners other than the first channel partner who are in a location of the first channel partner. Thereafter, the rating generation module determines which of the first set of SKUs have registered a decline in growth in order from the first channel partner over the predetermined period of time based on the analysis of the historic order data.
[0018] Finally, the rating generation module generates a rating for the
SKUs-channel partner combination. This rating indicates weightage to be assigned to the various logics as identified above, such as frequently ordered first set of SKUs, the deviation parameter of the first channel partner, the average order of the second set of SKUs, and the decline in growth in the order of the first set of SKUs, respectively. This rating is then used for identifying likely SKUs that may be recommended to the first channel partner.
[0019] Thus, the recommendation system for the tire SKUs enables
providing an end-user with a new data-driven way of interacting with the channel partners and enabling proactive order generation for various tire SKU groups. The present system may also be advantageous for the channel partners as they would be able to get a comprehensive view of each type of SKU along with its current availability.
[0020] The above-described recommendation system for the tire SKUs is
further described with reference to Figures 1 to 4. It should be noted that
the description and figures merely illustrate the principles of the present
subject matter along with examples described herein and should not be
construed as a limitation to the present subject matter. It is thus noted that
various arrangements may be devised that, although not explicitly described
or shown herein, describe the principles of the present subject matter.
Moreover, all statements herein reciting principles, aspects, and examples
of the present subject matter, as well as specific examples thereof, are
intended to encompass equivalents thereof.
[0021] Figure 1 illustrates a network environment 100 comprising a

system 102 for providing likely SKUs recommendation that may increase orders and range of SKUs provided by a tire manufacturer to their channel partners, according to an example of the present subject matter. The system 102 provides an end-user, for example, a field representative of a tire manufacturing company, a data-driven platform for interacting with a channel partner, thereby facilitating a proactive demand generation for tire SKU groups.
[0022] The system 102 may be accessed through a network 108 by a
locally installed SKU recommendation client 110 on at least one user device 106 or through browsers. Examples of the user device 106 may include but are not limited to a tablet, a smartphone, and similar devices. As shown in Figure 1, the user device 106 may be configured to receive inputs from end-users and communicate said inputs to the system 102, or components thereof.
[0023] For example, network 108 may be a single network or a
combination of multiple networks and may use a variety of different
communication protocols. Network 108 may be a wireless or a wired
network, or a combination thereof. Examples of such individual networks
include, but are not limited to, Global System for Mobile Communication
(GSM) network, Universal Mobile Telecommunications System (UMTS)
network, Personal Communications Service (PCS) network, Time Division
Multiple Access (TDMA) network, Code Division Multiple Access (CDMA)
network, Next Generation Network (NON), Public Switched Telephone
Network (PSTN). Depending on the technology, network 108 may include
various network entities, such as gateways, routers; however, such details
have been omitted for sake of brevity of the present description.
[0024] The network environment 100 may further include a central server
112. The central server 112 may comprise a central database 104 configured to store the various information that may be received, exchanged, generated, or stored to recommend likely tire SKUs, referred to as SKU recommendation information. The system 102 may be configured

to transmit and receive the SKU recommendation information over the network 108 to the central server 112. The central server 112 may thus serve as a repository of electronic, computer-readable information for the tire manufacturer, a field representative, and/or for a likely SKU recommendation generation authority, as examples. In this way, in certain embodiments, the SKU recommendation information may be submitted electronically via network 108 to the likely SKU recommendation generation authority, e.g., tire manufacturer.
[0025] The network environment 100 may also include a remote access
machine 114 to allow authorized individuals, such as channel partners, or organizations to communicate with the central server 112. The remote access machine 114 may include a central server access client 116, such as an internet browser, that executes on the remote access machine 114 and accesses the central server 112 via a network such as, for example, the network 108.
[0026] Based on the information provided by the end-users, such as the
field representatives, through the user device 106 and information available in the central database 104, the process of generating a recommendation for likely tire SKUs may be completed electronically. Thus, the system 102 provides an efficient mechanism for recommending products to field representatives and the channel partners so that they may choose the remunerative tire SKU groups easily based on the historical order data of the channel partners with the tire manufacturer without having to extract data through multiple sources and people. Also, with the help of present system 102, if a particular SKU is in stock, that can be recommended as opposed to one that is not in stock. This will ensure better inventory management. Additionally, the remote access of the system 102 to the channel partners may be helpful for them in directly ordering the tire SKU groups based on the recommendation generated by the system 102 without having to wait for receiving a communication from the field representative of the tire manufacturing company. For further explanation of the

implementation and operation of the system 102 to generate the
recommendation for likely SKUs, a reference is made to Figure 2.
[0027] Figure 2 illustrates the system 102 for providing recommendations
on selecting the tire SKUs according to another example implementation of the present subject matter. In an example, the system 102 depicted in Figure 2 may be a server, such as a web server communicatively coupled to the central server 112. For example, the system 102 may be connected to the central server 112 via the network 108. In another example, the system 102 may also be part of a hosted service executed on the central server 112.
[0028] The system 102 of the present invention provides a data-driven
platform for generating a recommendation for likely SKUs that may be used by the field representatives as well as the channel partners in choosing the right set of SKU groups.
[0029] As depicted in Figure 2, in an example implementation, the system
102 may include at least one processor 202 and a memory 204 coupled to the processor 202. In an example, the processor 202 may be implemented as microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. The memory 204 may include any computer-readable medium known in the art including, for example, volatile memory (e.g., RAM), and/or non-volatile memory (e.g., EPROM, flash memory, etc.). The memory 204 may also be an external memory unit, such as a flash drive, a compact disk drive, an external hard disk drive, or the like.
[0030] Also as depicted in Figure 2, in an example implementation,
interface(s) 206 may be coupled to the processor 202. The interface(s) 206 may include a variety of software and hardware interfaces that allow interaction of the system 102 with other communication and computing devices, such as network entities, external repositories, and peripheral devices. The interface(s) 206 may also enable the coupling of components

of the system 102 with each other. Further, in an example, the interface(s)
206 may couple the user device 106 to the system 102. Likewise, the
interface(s) 206 may couple the central server 112 and the system 102.
[0031] The system 102 may also comprise module(s) 208 and data 220
coupled to the processor 202. In one example, the module(s) 208 and data 220 may reside in the memory 204.
[0032] In an example, the data 220 may comprise historic order data 222,
a new product launch data 224, and other data 226. The module(s) 208 may include routines, programs, objects, components, data structures, and the like, which perform particular tasks or implement particular abstract data types. The module(s) 208 may further include modules that supplement applications on the system 102 for recommending likely tire SKUs, for example, modules of an operating system. The module(s) 208 further includes modules that implement certain functionalities of the system 102, such as processing the information received by the system 102 from the field representatives or the channel partners. The data 220 serves, amongst other things, as a repository for storing data that may be fetched, processed, received, or generated by one or more of the module(s) 208. In an example, the historic order data 222 may be received from the central database 104. The new product launch data 224 may comprise information on new products, such as SKU groups, that are being launched by the tire manufacturing company. The new product launch data 224 comprises data pertaining to new products launched by the tire manufacturing company. The new product launch data 224 may be chosen by the field representatives when the new products are launched by the tire manufacturing company to provide a static push to the orders of new products by pitching the new products to the channel partners.
[0033] To generate a recommendation for selecting an appropriate set of
tire SKU groups, the system 102 may require a certain logics basis on which the recommendation for likely SKUs can be generated. Accordingly, in an example embodiment, system 102 may include a rating generation module

210 that may be adapted to provide a rating for each of the logics on which the generation of recommendation for the likely SKUs depends. To generate such a rating, the rating generation module 210 first determines a first set of SKUs of a category that is frequently ordered by a first channel partner based on historic order data associated with a plurality of channel partners. The historic order data pertains to a predetermined period of time and maybe selected considering various factors affecting the order placements, such as economic factors, government policies, etc.
[0034] The historic order data may comprise a location of each of the
plurality of channel partners, a category of each SKUs that are ordered by each of the plurality of channel partners over a given period of time, and the details of the orders which could not be fulfilled successfully due to unavailability of the ordered tire SKUs. The category of the first set of SKUs may be filtered from amongst categories of the SKUs ordered by the channel partners.
[0035] The rating generation module 210 further determines average
order of the first set of SKUs that are placed by the first channel partner over
the predetermined period of time based on the historic order data.
[0036] The rating generation module 210 thereafter determines the
deviation parameter of the first channel partner based on the average order
of the first set of SKUs. The deviation parameter is indicative of deviation in
orders for the first set of SKUs by the first channel partner. For example,
considering that, based on data collected by the field representative, it is
known for the first channel partner that it orders 40 tire SKUs of a certain
category monthly, however, based on the historic order data, if it is
determined that out of 40, only 20 tire SKUs are being currently ordered
from a first tire manufacturing company to which the field representative is
associated, a difference of 20 SKUs that is being fulfilled by an entity other
than the first manufacturing company would be considered as the deviation
in orders by the rating generation module 210.
[0037] Accordingly, assuming that the system 102 is being used by the

first tire manufacturing company, the deviation parameter that is to be
determined for the first channel partner may be equal to the difference in
total SKU orders currently being placed by the first channel partner with the
first tire manufacturing company vis-à-vis their actual SKU requirement.
[0038] Furthermore, the rating generation module 210 determines
average order of a second set of SKUs that are ordered by channel partners other than the first channel partner who are in the location of the first channel partner. The determination of the average order of the second set of SKUs helps in identifying those groups of SKUs that are frequently ordered by the channel partners other than the first channel partner who is located in a geographical area same as the first channel partner deal in the same categories of SKUs.
[0039] For example, there may be carrying and forwarding agents (CFA)
who act as the last point from where the billing happens to the channel
partners. The CFA may be responsible for ensuring that the tires get
delivered to the channel partners. To each of the CFAs, multiple channel
partners may be assigned. So, in an example, if one CFA has been
assigned 10 channel partners, one channel partner out of these 10 channel
partners may be selected, and based on the average order of the tire
categories and the SKUs placed by said channel partner, it may be
assessed that which are the SKUs that other 9 channel partners order but
said channel partner does not order. Based on this assessment, a
recommendation may be provided to said channel partner to order those
SKUs that may have potential customer demand. Such a recommendation
may help said channel partner in possessing and selling all those tire SKUs
which are in demand and being sold by other channel partners of the area.
[0040] The rating generation module 210 also determines which of the
first set of SKUs have registered a decline in growth in order from the first channel partner over the predetermined period of time-based on the historic order data. For example, we may consider the historic order data for the last 3 months associated with the first channel partner. In that, month one is the

nearest one to the current month. So, if the current month is November,
month one will be October. Likewise, months two and three will be
September and August, respectively. We may look at the month three
orders for specific SKUs and, for each SKU, deduct that order from the
orders placed in the month two and one, respectively. From the final order
value, we may be able to assess whether there has been any decline in the
growth in order for SKUs by the first channel partner in three months.
[0041] The rating generation module 210 then generates a rating for the
SKUs-channel partner combination. This rating is indicative of weightage to be given to each of the above-discussed logics, such as the frequently ordered first set of SKUs, the deviation parameter of the first channel partner, the average order of the second set of SKUs, and the decline in growth in the order of the first set of SKUs, respectively, in identifying likely SKUs to be recommended to the first channel partner.
[0042] The rating generation module 210 may be configured to receive
an evaluation score for each of the above-discussed logics from the field representative or the channel partners. The rating to be given to each of the logics may depend upon the evaluation score given to each of these logics. For example, the rating generation module 210 may generate a rating as 'A', the highest, for the first logic, i.e., the frequently ordered first set of SKUs, when the logic is assigned evaluation score 100, the highest. The first logic is given the highest evaluation score as it represents the most likely SKU that the first channel partner would order because it is a running SKU. Likewise, the rating generation module 210 may generate a rating as 'B', the second highest, for the logic that indicates the decline in growth in the order of the first set of SKUs, when the logic is assigned an evaluation score of 90, the second highest. This logic is given the second highest evaluation score as it represents the SKU which may be the high order SKU but for some reason, its demand from the first channel partner has declined. In an example, it is possible to change the logics which may have an impact on the rating of the logics.

[0043] Once the rating for each of the logic is generated based on their
evaluation score, the ratings are then fed to an SKU recommendation
module 212. The SKU recommendation module 212 may then generate the
likely SKUs to be recommended to channel partners and field
representatives. In certain embodiments, the recommendation may be
generated for only those likely SKUs which are available in the stock of the
CFA. In certain embodiments, the recommendation on likely SKUs may be
generated periodically by the system 102, for example, every day, for
making use of the system 102 to check for the SKUs that may be
recommended to the channel partners and the field representatives.
[0044] Further, in certain cases, it may be possible that the first channel
partner places an order for a specific tire SKU, for example, truck tire SKU, however, due to the unavailability of the required number of stocks of said SKU with the tire manufacturer, the order either gets canceled or fulfilled partially leading to dissatisfaction for the channel partner and loss of order for the tire manufacturer.
[0045] To overcome such problems, the system 102 includes an
inventory management module 214. The inventory management module 214 identifies categories of the SKUs for which orders are not fulfilled due to their unavailability at a time of receiving the orders from the channel partners. This identification is done by analyzing the historic order data of the first channel partner with the tire manufacturer. Upon identifying any unfulfilled order in the historic order data of the first channel partner, the inventory management module 214 may notify the availability status of the unfulfilled categories of the SKUs to the channel partners. The availability status may indicate the number of available for the categories of the SKUs for which orders were not fulfilled previously.
[0046] In an example embodiment, the modules of the system 102 as
discussed above may be trained in an end-to-end fashion using various open-source machine learning models. For example, the SKU recommendation module 212 may be trained using a deep machine learning

model to enable it to recommend likely SKU to the end users, such as the channel partners and field representatives.
[0047] Likewise, in another example, the inventory management module
214 may be trained using an open-source machine learning model that enables it to identify unfulfilled SKU orders by analyzing historic order data, as discussed above. Also, some or all parameters of the modules may be learned through the training process.
[0048] For example, an open-source machine learning model may be
trained using training data that includes input data, such as historic order data, new product launch data, etc., and the correct or preferred output of the model for the corresponding input data. The machine learning model may repeatedly process the input data, and the parameters of the machine learning model may be modified in what amounts to a trial-and-error process until the model produces or “converges” on the correct or preferred output, such as generating a correct recommendation for selecting likely SKUs. This way, the system 102, by using a collaborative filtering deep learning model, may generate the likely SKUs to be recommended to the channel partners and field representative.
[0049] Figure 3 illustrates a method 300 for registration of tires within a
networked environment, in accordance with an example implementation of the present subject matter.
[0050] The order in which the method 400 is described is not intended to
be construed as a limitation, and any number of the described method
blocks may be combined in any order to implement method 400, or an
alternative method. Furthermore, the method 400 may be implemented by
processor(s) or computing device(s) through any suitable hardware, non-
transitory machine-readable instructions, or combination thereof.
[0051] It may be understood that blocks of the method 400 may be
performed, for example, by the above-described registration system 102 for tires, as illustrated in FIGS. 1 and 2. In an example, the system 102 for recommending likely tires SKUs may be installed in a network environment,

such as the network environment 100 described in reference to FIG.1.
[0052] The blocks of the method 300 may be executed based on
instructions stored in a non-transitory computer-readable medium, as will be
readily understood. The non-transitory computer-readable medium may
include, for example, digital memories, magnetic storage media, such as
magnetic disks and magnetic tapes, hard drives, or optically readable digital
data storage media.
[0053] Referring to Figure 3, at block 302, the rating generation module
210 determines a first set of SKUs of a category that is frequently ordered
by a first channel partner based on historic order data pertaining to a
predetermined period of time associated with a plurality of channel partners.
As discussed earlier, the historic order data comprises a location of each of
the plurality of channel partners and a category of each SKUs ordered by
each of the plurality of channel partners.
[0054] At block 304, the rating generation module 210 determines
average order of the first set of SKUs by the first channel partner over the
predetermined period of time-based on the historic order data.
[0055] At block 306, the rating generation module 210 determines a
deviation parameter of the first channel partner based on the average order
of the first set of SKUs. As already discussed above, the deviation
parameter is indicative of deviation in orders for the first set of SKUs by the
first channel partner.
[0056] At block 308, the rating generation module 210 determines
average order of a second set of SKUs ordered by channel partners other
than the first channel partner who are in the location of the first channel
partner.
[0057] At block 310, the rating generation module 210 determines which
of the first set of SKUs have registered a decline in growth in order from the
first channel partner over the predetermined period of time-based on the
historic order data.
[0058] At block 310, the rating generation module 210 generates a rating

for the SKUs-channel partner combination. As discussed already, the rating is indicative of weightage to be given to the frequently ordered first set of SKUs, the deviation parameter of the first channel partner, the average order of the second set of SKUs, and the decline in growth in the order of the first set of SKUs, respectively, in identifying likely SKUs to be recommended to the first channel partner.
[0059] The methods and devices of the present subject matter generate
a recommendation for the likely SKUs for the channel partners and the field representatives. With the help of the present recommendation system, the end-user, such as a field representative of the tire manufacturing company, would be able to gauge the channel partner's potential and pitch him SKU groups where there’s a scope of improvement in sales; evaluate what is being purchased by the channel partners nearby and not the channel partner in consideration; find out SKUs groups which were purchased by the channel partner but have been observing a declining trend in demand/sales; and promote SKU groups to the channel partner which is new. In other words, the methods and devices of the present subject matter allow for checking the stock of the SKUs in real-time before sharing the recommended SKUs with the field representative and dealers.
[0060] Although implementations have been described in a language
specific to structural features and/or methods, it is to be understood that the appended claims are not necessarily limited to the specific features or methods described. Rather, the specific features and methods are disclosed as examples of a system for recommending likely tire SKUs for the purposes such as selecting an appropriate tire SKU before placing the order.

I/We claim:
1. A system comprising:
at least one processor;
a memory in communication with the at least one processor;
a rating generation module coupled to the at least one processor, to:
determine a first set of stock keeping units (SKUs) of a category of tires frequently ordered by a first channel partner based on historic order data pertaining to a predetermined period of time associated with a plurality of channel partners, the historic order data comprising a location of each of the plurality of channel partners and a category of each of the SKUs ordered by each of the plurality of channel partners,
wherein the category of the first set of SKUs is from amongst categories of the SKUs ordered by the channel partners;
determine average order of the first set of SKUs by the first channel partner over the predetermined period of time based on the historic order data;
determine a deviation parameter of the first channel partner based on the average order of the first set of SKUs, the deviation parameter being indicative of deviation in orders for the first set of SKUs by the first channel partner;
determine average order of a second set of SKUs ordered by channel partners other than the first channel partner who are in location of the first channel partner;
determine which of the first set of SKUs have registered decline in growth in order from the first channel partner over the predetermined period of time based on the historic order data; and
generate a rating for SKUs-channel partner combinations, the rating being indicative of weightage to be assigned to the frequently ordered first set of SKUs, the deviation parameter of the first channel partner, the average order of the second set of SKUs, and the

decline in growth in order of the first set of SKUs, respectively, in identifying a SKU to be recommended to the first channel partner.
2. The system as claimed in claim 1, further comprising a SKU
recommendation module coupled to the at least one processor, to
receive the rating for the SKUs-channel partner combination; and generate a list of SKUs to be recommended to the first channel partner based on the rating for the SKUs-channel partner combination.
3. The system as claimed in claim 1, further comprising an inventory
management module coupled to the at least one processor, to
identify, based on the historic order data, categories of the SKUs for which orders are not fulfilled due to their unavailability at a time of receiving the orders from the channel partners.
4. The system as claimed in claim 4, wherein the inventory management
module is to also notify availability status of the unfulfilled categories of the
SKUs to the channel partners.
5. A method comprising:
determining a first set of stock keeping units (SKUs) of a category of tires frequently ordered by a first channel partner based on historic order data pertaining to a predetermined period of time associated with a plurality of channel partners, the historic order data comprising a location of each of the plurality of channel partners and a category of each of the SKUs ordered by each of the plurality of channel partners,
wherein the category of the first set of SKUs is from amongst categories of the SKUs ordered by the channel partners;
determining average order of the first set of SKUs by the first channel partner over the predetermined period of time based on the historic order data;

determining deviation parameter of the first channel partner based on the average order of the first set of SKUs, the deviation parameter being indicative of deviation in orders for the first set of SKUs by the first channel partner;
determining average order of a second set of SKUs ordered by channel partners other than the first channel partner who are in location of the first channel partner;
determining which of the first set of SKUs have registered decline in growth in order from the first channel partner over the predetermined period of time based on the historic order data; and
generating a rating for SKUs-channel partner combinations, the rating being indicative of weightage to be assigned to the frequently ordered first set of SKUs, the deviation parameter of the first channel partner, the average order of the second set of SKUs, and the decline in growth in order of the first set of SKUs, respectively, in identifying a SKU to be recommended to the first channel partner.
6. The method as claimed in claim 5, further comprising:
receiving the rating for the SKUs-channel partner combination; and
generating a list of SKUs to be recommended to the first channel
partner based on the rating for the SKUs-channel partner combination.
7. The method as claimed in claim 5, further comprising:
identifying, based on the historic order data, categories of the SKUs
for which orders are not fulfilled due to their unavailability at a time of receiving the orders from the channel partners.
8. The method as claimed in claim 7, further comprising:
notifying availability status of the unfulfilled categories of the SKUs to the channel partners.