Big Data Analytics, commonly called Big Data, is the inductive process of examining data sets to uncover information such as patterns, correlations, trends and preferences to make informed business decisions and forecasts.
The data sets used for Big Data are composed by both:
- quantitative data
- qualitative data
The most important thing is that Big Data works with both
- structured data
- non-structured data
This means that, differently from the classic Business Intelligence, Big Data can upload and examine databases made by both
as well as pulling data from
- corporate datasets
- external datasets
What makes this possible is the use of Artificial Intelligence and, in particular, of Deep Learning.
Nowadays, there are 3 main problems that can be solved with AI
- Regression Problems: this could be applied whenever the output of a subset of inputs is a continuous function
- Classification Problems: this could be applied whenever the output of a subset of inputs is a discrete function
- Clustering Problems: this could be applied whenever the output of a subset of inputs is not predictable/known
The 3 problems are solved by using sequences of algorithms called Neural Networks.
Usually, every Neural Network performs 4 activities:
- Data Collection
- Data Cleaning
- Patterns Identification
- Prediction Making
To better understand how Big Data works let’s walk through a process step by step.
One of the most interesting applications of Big Data and AI is at Heineken.
Heineken is a Dutch brewing company, founded in 1864 by Gerard Adriaan Heineken in Amsterdam.
Since the 70s, under the guidance of Alfred Henry Heineken, the company has grown through acquisitions and today is one the three biggest breweries in the world with more than 70 thousand employees and 20 billion euros of revenues.
To jump on top of the beer market, Heineken made massive investments in Big Data and AI in order to optimize every stage of its Supply Chain with the main focus on the company’s Demand Forecasting and Stock Strategy.
Usual Demand Forecast is calculated on a statistical regression based on historical Corporate Data (i.e. historical series of sales per region).
The statistical regression is based on 4 components:
- Constant: it is the minimum quantity that is sold per period
- Trend: represents a growth/decrease in historical sales
- Seasonality: takes into account particular peaks in the sales that occur during the year
- Random: it is a white noise that is embedded in the historical data that is removed before calculating the Demand Forecast
Heineken’s idea was to teach a machine how to break-down the Random component by taking into account External Data such as
- Weather Forecast
- Special Events (i.e. a Football match or a Music Festival)
- Trends on the Social Networks (i.e. influencers monitoring)
In order to do that, Heineken went through:
- Step 1. Data Collection:
- Corporate Datasets containing Historical Data Series are stored
- Crawling the internet, Web Data are stored by using AI Vision Systems able to solve Clustering Problems for extracting information from qualitative/non-structured data
The output of this phase is the Raw Data on which calculating a Demand Forecast
- Step 2. Data Analysis:
- Using a Clustering Analysis, Historical Data Series and Web Data are grouped in sets of related objects in such a way that it is possible to explain a random behaviour of the sales by connecting it with an external event
- Using Predictive Analytics, the clustered Raw Data are used to calculate a Demand Forecast that takes into account what was previously discarded as a random component
Heineken’s usage of Big Data Analytics and AI
- Improved the forecast error
- Changed the Stock Strategy in order to optimize it based on External Data
leading to reduced Working Capital that is fundamental for freeing Capital for a company that grows through acquisitions.
Business Strategy | Product Marketing | Executive Master eCommerce Management | Business Innovation Master | MSc
I am driven by my personal growth and of people/contexts that surround me.
I followed a professional path in Valentino Fashion Group and Luxottica during which, thanks to the ability to understand different businesses and interests, I was able to succeed in Operations, Merchandising and Retail.
These organizations have exploited my ability to mediate and translate needs/constraints into practice, assigning me to Project Management roles.
Luxottica relied on my ability to analyze, to anticipate things and to imagine/implement solutions by appointing me in Supply Chain Management department and assigning me to the Product Management of IoT solutions for Anti-counterfeiting and Retail digitalization.
During this professional path, I also developed my leadership by managing teams to build Processes, Organizations, Systems and Governance Tools.