Hierarchical neural network based implementation for predicting out of stock products
View Patent ↗A hierarchical neural network for predicting out of stock products comprises an input layer that receives data from data sources that store disparate datasets having different levels of attribute detail pertaining to products for sale in stores of a retailer. A first level of neural networks processes the data from the data sources into respective learned intermediate vector representations. A second level comprises a concatenate layer that concatenates the learned intermediate vector representations from the second level into a combined vector representation. A third level comprises a feed forward network that receives the combined vector representation and outputs to the retailer an out of stock probability indicating which store and product combinations are likely to have out of stock products over a predetermined timeframe.
1 . A system for predicting out of stock (OOS) products, the system, comprising:
one or more processors executing a hierarchical neural network (HNN), the HNN comprising:
one or more data sources that store disparate datasets having different levels of attribute detail pertaining to products for sale in one or more stores of a retailer, the disparate datasets comprising:
low-level store data including daily store visits and past occurrences of out of stock products, categorical data including store identifiers and associated city identifiers, store-level product data, and time-series product sales data including monthly or weekly sales per product;
a first level that processes the low-level store data, the categorical data, the store-level product data, and the time-series product sales data from the one or more data sources into respective learned intermediate vector representations, the first level comprising:
a convolutional neural network (CNN) layer that processes the low-level store data;
an embedding layer that processes the categorical data;
a long short-term memory (LSTM) layer that processes the time-series product sales data;
a second level comprising a concatenate layer that concatenates the learned intermediate vector representations from the second level into a combined vector representation; and
a third level comprising a feed forward network that receives the combined vector representation and outputs to the retailer an OOS probability indicating which store and product combinations are likely to have OOS products over a predetermined timeframe.
2 . The HNN of claim 1 , wherein the first level first translates the low-level store data, the categorical data, the store-level product data, and the time-series product sales data into initial vector representations.
3 . The HNN of claim 2 , wherein a set of initial vector representations representing the store-level product data are not processed by the first level but passed on to the second level.
4 . The HNN of claim 3 , wherein the concatenate layer concatenates the set of initial vector representations of the store-level product data with the respective learned intermediate vector representations.
5 . The HNN of claim 1 , wherein the CNN layer is based on a shared-weight architecture of convolution kernels that slide along the visit data and the visit data is convolved with one of the convolutions kernels to provide feature maps, where ones of the feature maps learn different features.
6 . The HNN of claim 5 , wherein the CNN layer includes a first attention layer such that the CNN layer processes low-level granular and sequential features and the first attention layer examines data from a predefined time period relevant to generating the OOS probability.
7 . The HNN of claim 1 , wherein the embedding layer processes the store identifiers and the city identifiers to capture information including interaction of the stores and cities with other variables.
8 . The HNN of claim 1 , wherein the LSTM layer includes stacked LSTM layers to learn historical patterns that are represented by LSTM state vectors, wherein the LSTM state vectors are fed into a second attention layer to enable the LSTM layer to examine data from a predefined time period relevant to generating the OOS probability.
9 . The HNN of claim 1 , wherein the one or more data sources are stored in: i) a data center of a service provider, ii) by a cloud service provider, iii) local to server comprising the one or more processors, or iv) by a computer system of the retailer or a consumer goods company.
10 . A method for implementing a hierarchical neural network (HNN) for predicting out of stock (OOS) products, the HNN executed by a computer server, the method comprising:
receiving one or more data sources that store disparate datasets having different levels of attribute detail pertaining to products for sale in one or more stores of a retailer, the disparate datasets comprising: low-level store data including daily store visits and past occurrences of out of stock products, categorical data including store identifiers and associated cities, store-level product data, and time-series product sales data including monthly or weekly sales per product;
processing, by a first level, the low-level store data, the categorical data, the store-level product data, and the time-series product sales data from the one or more data sources into respective learned intermediate vector representations, the first level comprising:
a convolutional neural network (CNN) to process the low-level store data, an embedding layer to process the categorical data; and a long short-term memory (LSTM) layer to process the time-series product sales data;
concatenating, by a second level comprising a concatenate layer, the respective learned intermediate vector representations into a combined vector representation; and
receiving, by a third level comprising a feed forward network, the combined feature vector representation and outputting to the retailer an OOS probability indicating which store and product combinations are likely to have OOS products over a predetermined timeframe.
11 . The method of claim 10 , further comprising translating the low-level store data, the categorical data, the store-level product data, and the time-series product sales data into initial vector representations.
12 . The method of claim 10 , further comprising generating a set of initial vector representations representing the store-level product data, and passing the set of initial vector representations on to the second level instead of the first level.
13 . The method of claim 12 , further comprising concatenating, by the concatenate layer, the set of initial vector representations of the store-level product data with the respective learned intermediate vector representations.
14 . The method of claim 10 , further comprising basing a CNN layer on a shared-weight architecture of convolution kernels that slide along the visit data and the visit data is convolved with one of the convolutions kernels to provide feature maps, where ones of the feature maps learn different features.
15 . The method of claim 14 , further comprising providing the CNN layer with a first attention layer such that the CNN layer processes low-level granular and sequential features and the first attention layer examines data from a predefined time period relevant to generating the OOS probability.
16 . The method of claim 10 , further comprising processing, by the embedding layer, the store identifiers and the city identifiers to capture information including interaction of the stores and cities with other variables.
17 . The method of claim 10 , further comprising providing the LSTM layer with stacked LSTM layers to learn historical patterns that are represented by LSTM state vectors, and feeding the LSTM state vectors into a second attention layer to enable the LSTM layer to examine data from a predefined time period relevant to generating the OOS probability.
18 . The method of claim 10 , further comprising storing the one or more data sources in: i) a data center of a service provider, ii) by a cloud service provider, iii) local to server comprising the one or more processors, or iv) by a computer system of the retailer or a consumer goods company.
19 . A non-transitory machine-readable storage medium that provides instructions that, if executed by a processor are configurable to cause said processor to perform operations comprising:
receiving data from one or more data sources that store disparate datasets having different levels of attribute detail pertaining to products for sale in one or more stores of a retailer, the disparate datasets comprising: low-level store data including daily store visits and past occurrences of out of stock (QOS) products, categorical data including store identifiers and associated cities, store-level product data, and time-series product sales data including monthly or weekly sales per product;
processing, by a first level, the low-level store data, the categorical data, the store-level product data, and the time-series product sale data from the one or more data sources into respective learned intermediate vector representations, the first level comprising: a
convolutional neural network to process the low-level store data, an embedding layer to process the categorical data; and a long short-term memory (LSTM) layer to process the time-series product sales data;
concatenating, by a second level comprising a concatenate layer, the respective learned intermediate vector representations into a combined vector representation; and
receiving, by a third level comprising a feed forward network, the combined feature vector representation and outputting to the retailer an OOS probability indicating which store and product combinations are likely to have OOS products over a predetermined timeframe.