1) Baseline Prediction
2) Uplift Prediction
3) Promotion Optimization
4) Promotion Plan Optimization
5) Flexible Modelling
It is necessary to know all data related customer purchase. We need high quality historical data for trade promotion. By using these data, we can analyze the customer’s choice based on the factors such as seasonality, trend and base price of the product. By analyzing these data in order to make system reliable and automated.
Since system need historical data to predict promotion uplifts that can be calculated based on total sales and revenue. System can work on new data. If there is any modification in data, promotion uplift can be recalculated easily.
System can identify best product based on the factors such as time, price and available budget. System enables to identify best product at the end of planning cycle.
Promotion Plan Optimization
By using positive and negative historical data application can build a new promotional plan. Promotional plan can be generated based on underlying models and data to decide on the frequency, duration.
Uses the best modelling to provide accurate results. Tool uses multiple models each model for different tasks.
Unit sales (input): Unit sales of product is competitive factor affecting the customer behaviors, especially for independent retailers. It is processed as quantitative information.
Product quality (input): This factor includes the evaluation about product quality according to customers via a 1-9 scale. It is processed as qualitative information.
Customer satisfaction level (input): This factor shows the sales and post-sales behaviors of retailers to the customers. It is processed as qualitative information.
Effect of promotions, holidays and special days (input): This factor means the percent increase of sales related to promotions or special days (such as feasts, new year's day, etc.). It is processed as qualitative information.
Product quantity (output): Product quantity is the quantity from customers to retailers. It is processed as quantitative information.
We will use Multi-Layer Perceptron (MLP) and Backpropagation algorithm which will be used to train the data
However, we will concentrate on nets with units arranged in layers
Multi-Layer Perceptron Methodology works on non-linear separable data
Following are steps of algorithm
Initialize weights at random, choose a learning rate n
Until network is trained:
For each training example (input pattern and target outputs):
Present inputs for the first pattern to the input layer
Sum the weighted inputs to the next layer and calculate their activations using activation function formula
Present activations to the next layer, repeating (2) until the activations of the output layer are known
Compare output activations to the target values for the pattern and calculate deltas for the output
Propagate error backwards by using the output layer deltas to calculate the deltas for the previous layer
Use these deltas to calculate those of the previous layer, repeating until the first layer is reached
Calculate the weight changes for all weights and biases (treat biases as weights from a unit having an activation of 1)
If training by pattern, update all the weights and biases, else repeat the cycle for all patterns, summing the changes and applying at the end of the epoch
Trade promotion using Artificial Intelligence enable customers to make sensible choices. Trade promotion using Artificial Intelligence allows retailers to gain sharper predicting tools that ensure to make sharper business decisions. This tool combines trade promotion with Artificial Intelligence to offer innovative business solution. Innovative software solution will help organizations to address business goals and achieve high performance.