Thousands of new products: when to order and how many?

Which ones to produce and how many? How to manage inventory levels? How to choose? Which products to choose and how many?

Indecision is the worst decision
In the retail sector, the choice of the optimum quantity for the first order of a product becomes more complex when we are faced with a situation in which there is a very wide range of products with a high rate of annual turnover. Moreover, very often the time between order and delivery can be a matter of months. Under these conditions, it can be difficult to make the first order in terms of minimising the risks of an incorrect estimate, unforeseen storage costs or running out of stock early.

Our guiding idea
The traditional approach based on historical sales is of no use where no such history exists, as is the case with new products. It is therefore necessary to take a different approach, starting perhaps from the idea that every product actually involves a mix of already existing features. By combining factors such as historical sales of similar products, stock levels, prices, product features, scheduling, as well as marketing and discount campaigns, it is possible to devise a predictive model able to determine the correct quantity of new products to be ordered by analogy.

Not just a theory
The solution is based on Open Source technologies specialised in Big Data processing. The data is collected in a central Data Lake using Cloudera distribution and is processed by attribute-based algorithms that make predictions based on the data. Starting from the features of the product and by exploiting the history of similar products, forecasts are calculated using ARIMA models and neural networks. The results are displayed to users using monitoring dashboards. To make the results more robust and reliable, a data pre-processing stage was added, during which the data is cleaned and standardised to eliminate exogenous events involving an increase or decrease in sales.

So what are the actual benefits?
The forecasting and recommendation solution developed and implemented by Data Reply is particularly useful in areas where a lack of information, about historical sales, for example, does not allow conscious choices to be made. By refining the logics and algorithms used, we now have a model capable of providing forecasts for new products covering a period of up to 12 months in the future, with another 6 months of advance knowledge regarding their commercialisation. The business therefore gains an effective tool for optimally planning its orders and market strategy.

Data Reply is the Reply group company that specialises in big data, data science and artificial intelligence. We are building experience across four main business sectors: Sales and Marketing Intelligence, Big Data Engineering & Security Intelligence, Enterprise Intelligence, IoT & Industry 4.0 Intelligence. The more than 40 projects currently in production include the creation of Data Lakes and the use of Artificial Intelligence and Machine Learning algorithms. An innovative approach based on quantum computing supports the development of algorithms. We also offer training programmes on Data Science and Deep Learning.