Artificial Intelligence for price prediction

We explain what is price forecasting, how AI can help and what are the business benefits of AI for price prediction

While AI is being intensively used in the financial sector to help financial analysts make the relevant decisions, there is still an untapped potential in many other sectors. This post explains why AI is a game changer for price forecasts.

Price forecasting

What is price forecasting?

Price forecasting (or predictive pricing, or price prediction) is the action of predicting the price of a commodity/product/service by evaluating various factors like its characteristics, demand, seasonal trends, prices of other commodities, offers from numerous suppliers etc.

Businesses often use price forecasting to organize their supply chain, plan their sales or plan their budget.

How is price forecasting traditionally done

Many businesses rely either on analyses from business experts, or on statistical models. Unfortunately, these techniques are not always able to reflect the complexities of the factors impacting the evolution of prices.

Why AI can help

For price prediction, Machine Learning provides a unique way of incorporating two complementary approaches : technical analysis and fundamental analysis. While technical analysis solely looks at historical prices, fundamental analysis consists of understanding the external and internal factors that influence the price of a certain commodity, product or service.

How AI impacts price forecasts

We are going to evaluate three aspects in which AI disrupts price forecasting:

AI can cope with price volatility

The term “price volatility” is used to describe price fluctuations of a product or asset. It is measured by the day-to-day percentage difference in the price of a certain product. What defines a volatile market is the degree of variation in prices. The wider the price ranges from low to high on a daily, weekly, monthly or yearly basis - the higher the volatility and vice versa.

Volatility is important because it provides a measure of price uncertainty in markets. The effect of volatility is generally seen as negative, because it brings uncertainty about future price levels. Being able to accurately predict and estimate volatility are crucial in various fields like option pricing, risk management and portfolio management.

Artificial Intelligence and Machine Learning are capable of coping with price volatility. An AI algorithm can be capable of simultaneously taking into account multiple factors that are affecting the price volatility. This can be for example supply and demand, storage levels and transportation constraints, geopolitics, seasonality and market information. Sophisticated algorithms, unlike simple models, can, under certain conditions predict the likelihood of future events based on past events.

AI can cope with multiple data sources

What makes price prediction often hard is the multiplicity of data sources, and their various formats. In AI, too much data is not a problem but an asset, if this data is selected and used properly. Many more insights can actually be gained by combining these different data sources. Here is an overview of the types of data sources that can be used in Artificial Intelligence. With AI, public and private sources of data that contain a lot of valuable insights that can be processed to generate hidden insights. Data gathered from markets, internal datasets, and open data from public authorities can be used to train an Artificial Intelligence algorithm to predict future levels of prices. The relationships between different data sources can be extremely valuable, and AI can help combine data sources intelligently and fully analyze properties from multiple data points. Furthermore, the algorithm is adaptively improving its performance as the number of input data samples for “learning” increases. Hence, the accuracy of the price prediction model will increase as more sources are collected during the development stage.

AI can cope with complex value chains

In businesses where value chains are complex and moving fast, having clear and transparent insights provides a competitive advantage over competitors. Making sense of movements within complex, distributed value chains is extremely hard for a human, especially in a volatile world.
An AI model can perceive, correlate and analyze sometimes very subtle changes. As a result, it can help a user make an optimal decision, in a limited timeframe, with a clear analysis of the parameters used to make this decision.

What are the business benefits of AI for price prediction

Price prediction with AI improves the decision making process

Traditional price forecasting methods often have limited accuracy. That is why making a decision based on these forecasts can be a difficult task.

AI makes prediction better, faster and cheaper. Better predictions matter when you make decisions in the face of uncertainty, as every business does, constantly.
By providing you with a reliable forecast, AI price forecast solutions can enable you to focus on strategy and decision, enabling you easier and faster decision making throughout the organization.

Adjust your sales and/or procurement strategy

Knowing how the prices will evolve in the future, can give you a competitive edge over your competitors, clients or suppliers. For example, by knowing the evolution of a price, you will be able to purchase more when the price is at a year low, or simply negotiate the best sales or procurement contract.


Making the right decision about a price is complex, especially in the case of a new customer, volatile market, or a large pool of diverse customers. Knowing how the future prices will evolve enables you to adapt your prices or discounts at a given frequency so you can optimize your margins depending on the demand, stocks and so on.

By knowing the evolution of future prices, you can simultaneously purchase and sell an asset to profit from an imbalance in the market. It is a trade known as arbitrage, that allows you to exploit the price differences of identical or similar financial instruments in different markets. Arbitrage exists as a result of market inefficiencies, and would therefore not exist if all markets were perfectly efficient.

Improve company operations and supply chain

AI enables companies to source and sell products at the right price, but it is only one piece of the puzzle. Companies that are looking to become or remain leaders of their industry will couple price prediction with other applications such as sales forecasting to optimize their SCM (supply chain management) and their profits.

Kantify and Price Forecast

As passionate problem solvers, one of our expertise includes building best-in-class AI price prediction solutions. The Kantify Price Prediction solution identifies the future movement of the prices, and what are the main drivers of the price evolution. We can also generate what-if-scenarios, as well to understand how prices will evolve if certain parameters change. Read more about our latest case study in price prediction here.

If you are curious how your organization can implement AI to make smarter and data driven decisions, leave us a message or book a 15min slot to discuss your idea and have a first exchange (in English, French or Dutch).


How AI can help companies in times of crisis
We selected four ways in which Artificial Intelligence can help reduce profit loss, and help your business exit the crisis even stronger than before. Read More
Artificial Intelligence and the COVID-19 Black Swan
COVID-19 has been named a Black Swan, but it was predictable. Here is why and how.Read More
Who should be your AI project manager
We share some lessons we learned from running AI projects, on how to appoint the best person in charge of your new AI project managementRead More
5 key resources to get started with AI
Five online resources to help you learn AI and Machine Learning, whether you are a tech geek or simply just beginning to dive in the world of AIRead More
Short overview of Machine Learning techniques
In this article we cover four major types of machine learning techniques, we explain their applications and help you differentiate themRead More
What are the main errors to avoid when starting in AI as a company?
We have listed some errors to avoid before planning AI implementation in your businessRead More
Difference between Data Science, Machine Learning and Artificial Intelligence
We help in understanding the difference between DS, ML and AI and when to use each of themRead More
What is a Proof of Concept (and how to make the most of it)?
We explain what is a Proof of Concept, and how can it be leveraged in order to minimize risk and maximize ROIRead More
Case Study: Amazon, Customer Retention and AI
We analyse Amazon's customer retention success story, and share business lessions on how the use of AI in sales and marketing can improve customer experienceRead More