AI for demand forecasting in the food industry

AI for demand forecasting in the food industry

The concept of a balance point between supply and demand is used to explain various situations in our daily lives, from bread in the neighborhood bakery, which can be sold at the equilibrium price, which equals the quantities desired by buyers and sellers, to the negotiation of securities of companies in the stock market.

On the supply side, a definition of the correct price to be practiced and mainly the quantity are common issues in the planning and execution of the strategy of several companies.

In this context, how are technological innovations in the data area establishing themselves in the food sector?

The construction of the demand forecast

The projection of demand is often built through historical sales data, growth prospects for the sector or even targets set to engage sales of a certain product.

When considering only these means of forecasting, without considering the specific growth of each SKU (Stock Keeping Unit), companies can fall into the traps of subjectivity or generalism.

The expansion of a sector does not result in a growth of the same magnitude for the entire product mix. For example, does a projected annual growth of 6% for the food sector necessarily imply equivalent growth for the noble meat segment?

Possibly not, as this market niche may be more resilient or sensitive than the food sector, or it may even suffer from recent changes in consumer habits.

Impacts of Demand Forecasting Errors

For companies, mainly large ones with economies of scale and geographic capillarity, an error in the forecast of demand can cause several consequences, such as:

  • Stock break;
  • Perishable waste (What is FIFO?);
  • Drop in production;
  • Idle stock (slow moving)
  • Pricing errors

Adversities like these directly impact the companies’ final results, as they result in loss of market share, increase in costs or low optimization in the dilution of fixed costs, growth in the loss of perishable products, frustration of employees in relation to the goals and mainly break in the confidence of recurring customers who depend on supply for their operations.

The demand forecast in the food sector

The food industry is situated in a context of highly perishable products with the following characteristics:

  • High inventory turnover;
  • Parallel supply in different locations;
  • Large number of Skus, points of production and points of sale;
  • Verticalized supply chain;
  • Non-linearity in data patterns;
  • Seasonality.

These characteristics make the sector a business niche that is more sensitive to deviations in demand forecast and adjacent planning.

Supply chain opportunity

As an alternative to the traditional demand forecast format, there are opportunities to use market and AI data to assist managers in the S&OP (Sales & Operations Planning) process, as well as in the S&OE (Sales and Operations Execution) process.

During the S&OP process, demand forecasting supported by AI facilitates the work of the marketing and sales areas, as well as reducing uncertainty and increasing predictability for the supply chain areas.

In the S&OE process, AI can be used to identify new opportunities and to correct deviations from what was planned.

In addition to the technical attributes that AI can add to the process, the data base reduces points of conflict between teams, reduces historical disputes between preferences for SKUs and makes the process more transparent between areas.

Previously, in our blog, we addressed the challenges of forecasting demand in our view (pt. 1 in portuguese). In the articles, we cite the differentials of the predictive approach in relation to demand, taking into account factors such as seasonality, geographic / regional preferences and changes in consumer behavior.

We understand that the need for a predictive approach through data, mainly external to the company, is increasingly latent.

The role of machine learning in the food sector

The use of AI through machine learning techniques associated with a coherent technological stack of analytics (What is a technological stack?) Provides greater information speed, data organization with different granularities (region, state, city and neighborhood), adjustments seasonality, exploration of opportunities and decision making in real time.

In the case of the food sector, the greatest accuracy in forecasting demand means:

  • Inventory optimization among Distribution Centers (CDs);
  • Reduction of idle stocks;
  • Decrease in disruptions that cause loss of market share due to substitute products;
  • Direct reduction in losses with perishability (FIFO).

The great technical and conceptual challenge faced by data scientists (The profile of data scientists in the view of Aquarela), however, is the modeling of analysis datasets (what are datasets?) That will serve for the proper training of machines.

Please note that:

“Performing machine training with data from the past alone will cause the machines to replicate the same mistakes and successes of the past, especially in terms of pricing, so the goal should be to create hybrid models that help AI replicate with more intensity and emphasis the desired behaviors of the management strategy “.

In the case of Aquarela Analytics, the demand forecast module of Aquarela Tactics makes it possible to obtain forecasts integrated into corporate systems and management strategies. It was created based on real national-wide retail data and algorithms designed to meet specific demands in the areas of marketing, sales, supply chain, operations and planning (S&OP and S&OE).

Conclusions and recommendations

In this article, we present some key characteristics of the operation of demand forecasting in the food sector. We also comment, based on our experiences, on the role of structuring analytics and AI in forecasting demand. Both are prominent and challenging themes for managers, mathematicians and data scientists.

Technological innovations in forecasting, especially with the use of Artificial Intelligence algorithms, are increasingly present in the operation of companies and their benefits are increasingly evident in industry publications.

In addition to avoiding negative points of underestimating demand, the predictive approach, when done well, makes it possible to gain market share in current products and a great competitive advantage in forecasting opportunities in other niches before competitors.

What is Aquarela Advanced Analytics?

Aquarela Analytics is Brazilian pioneering company and reference in the application of Artificial Intelligence in industry and large companies. With the Vortx platform and DCIM methodology, it serves important global customers such as Embraer (aerospace), Randon Group (automotive), Solar Br Coca-Cola (food), Hospital das Clínicas (health), NTS- Brazil (oil and gas), Votorantim (energy), among others.

Stay tuned following Aquarela’s Linkedin!

14 sectors for applying Big Data and their input datasets

14 sectors for applying Big Data and their input datasets

Hello folks, 

In the vast majority of talks with clients and prospects about Big Data, we soon realized an astonishing gap between the business itself and the expectations of Data Analytics projects. Therefore, we carried out a research to respond the following questions: 

  • What are the main business sectors that already use Big Data?
  • What are the most common Big Data results per sector?
  • What is the minimum dataset to reach the results per sector

The summary is organized in the table below.

,Business type / sector,Raw data examples,Business Opportunities,, ,"1 - Bank, Credit and Insurance ","Transaction history. Registration forms. External references such as the Credit Protection Service. Micro and macro economic indices. Geographic and demographic data.","Credit approval. Interest rates changes. Market analysis. Prediction of default . Fraud detection. Identifying new niches. Credit risk analysis.",, ,2 - Security,"Access history. Registration form. Texts of news and WEB content.",Pattern detection of physical or digital behaviours that offer any type of risk.,, ,3 - Health,"Medical records. Geographic and demographic data. Sequencing genomes.","Predictive diagnosis (forecast). Analysis of genetic data. Detection of diseases and treatments. Map of health based on historical data. Adverse effects of medications / treatments.",, ,"4 - Oil, gas and electricity",Distributed sensor data.,"Optimization of production resources. Prediction / fault and found detection.",, ,5 - Retail,"Transaction history. Registration form. Purchase path in physical and/or virtual stores. Geographic and demographic data. Advertising data. Customer complaints.","Increasing sales by product mix optimization based on behaviour patterns during purchase. Billing analysis (as-is, trends), the high volume of customers and transactions, credit profile by regions. Increasing satisfaction / loyalty.",, ,6 - Production,"Data management system / ERP production. Market Data.","Optimization of production over sales. Decreased time / amount of storage. Quality control.",, ,7 - Representative organizations,"Customer's registration form. Event data. Business process management and CRM systems.","Suggestion of optimal combinations of company profiles, customers, business leverage to suppliers. Synergy opportunities identification.",, ,8 - Marketing,"Micro and macroeconomic indices. Market research. Geographic and demographic data. Content generated by users. Data from competitors. ","Market segmentation. Optimizing the allocation of advertising resources. Finding niche markets. Performance brand / product. Identifying trends.",, ,9 - Education,"Transcripts and frequencies. Geographic and demographic data. ","Personalization of education. Predictive analytics for school evasion.",, ,10 - Financial / Economic,"List of assets and their values. Transaction history. Micro and macroeconomics indexes.","Identify the optimal value of buying complex assets with many analysis variables (vehicles, real estate, stocks, etc.). Determining trends in asset values. Discovery of opportunities.",, ,11 - Logistic,"Data products. Routes and delivery points.","Optimization of goods flows. Inventory optimization.",, ,12 - E-commerce,"Customer registration. Transaction history. Users' generated content.","Increased sales through automatic product recommendations. Increased satisfaction / loyalty.",, ,"13 - Games, social networks and platforms (freemium)","Access history. Registration of users. Geographic and demographic data.",Increase free users conversion rate for paying users by detecting the behaviour and preferences of users. ,, ,14 - Recruitment,"Registration of prospects employees. Professional history, CV. Conections on social networks.","The person's profile evaluation for a specific job role. Criteria for hiring, promotions and dismissal. Better allocation of human resources.",,

Conclusions

  • The table presents a summary for easy understanding of the subject. However, for each business there are many more variables, opportunities and of course, risks. It is highly recommended to use multivariate analysis algorithms to help you prioritize the data and reduce project’s cost and complexity.
  • There are many more sectors in which excellent results have been derived from Big Data and data science methodology initiatives. However we believe that these can serve as examples for the many other types of similar businesses willing to use Big Data.
  • Common to all sectors, Big Data projects need to have relevant and clear input data; therefore it is important to have a good understanding of these datasets and the business model itself. We’ve noticed that currently many businesses haven’t been yet collecting the right data in their systems, which suggests the need pre-Big Data projects. (We will write about this soon). 
  • One obstacle for Big Data projects is the great effort to collect, organize, and clean the input data. This can surely cause overall frustration on stakeholders.
  • At least as far as we are concerned, plug & play Big Data solutions that automatically get the data and bring the analysis immediately still don’t exist. In 100% of the cases, all team members (technical and business) need to cooperate, creating hypothesis, selecting data samples, calibrating parameters, validating results and then drawing conclusions. In this way, an advanced scientific based methodology must be used to take into account business as well as technical aspects of the problem.

What is Aquarela Advanced Analytics?

Aquarela Analytics is Brazilian pioneering company and reference in the application of Artificial Intelligence in industry and large companies. With the Vortx platform and DCIM methodology, it serves important global customers such as Embraer (aerospace), Randon Group (automotive), Solar Br Coca-Cola (food), Hospital das Clínicas (health), NTS- Brazil (oil and gas), Votorantim (energy), among others.

Stay tuned following Aquarela’s Linkedin!