Why Your AI Needs Human Intervention 

You’re reviewing yesterday’s numbers and something looks off. Margins are thinner than they should be. The market moved and nobody told you. Your pricing stayed static while surrounding stations didn’t. Your strategy was stale and your margins are gone.

This is what happens when AI operates without guardrails. Our AI-enabled retail fuel pricing solution, A2i PriceCast, includes critical guardrails, including human oversight and intervention.

You’re the Strategist. The AI Is Your Superpower.
AI isn’t here to replace your judgment. It’s here to amplify it. You know your market and understand your customers. Algorithms can’t replicate the “why” for prices moving up or down – only you can. It doesn’t know if a competitor is going out of business, clearing old stock, or just baiting a price war.

A2i PriceCast enables you to analyze your own historical transaction data and customer behavior patterns. It surfaces pricing opportunities you wouldn’t spot in a spreadsheet. It delivers a clear recommendation, with the math to back it up. And, that’s the superpower! Seeing what the data sees, at a speed and scale no spreadsheet can match and then deciding what to do with it.

But nothing happens until you say so. Every recommendation requires your approval before any price change. This is principle number one at A2i: augmentation, not automation. The AI does the analysis. You make the call.

Your Data Stays Yours
Data isolation is fundamental to how A2i PriceCast operates.

Data Silos Are Non-Negotiable
Every A2i PriceCast customer gets their own isolated environment. Your data trains your model, not your competitor’s, not the station down the street. Yours alone.

No Cross-Contamination
Our AI algorithms are trained with data from only one customer at a time. Your pricing patterns stay confidential. Your market insights remain in your vault.

You Own Everything
Your data isn’t ours to monetize, analyze for others, or use to improve the platform. It belongs to you. We’re the custodians, nothing more.

Every Recommendation Has a Paper Trail
When A2i PriceCast recommends a price, you see exactly:

• Which data and customer behavior patterns it analyzed
• What demand and elasticity signals it detected
• How it reached that specific recommendation
• What strategy rules it followed (the ones you set)

You can trace every recommendation back to real data, historical performance, publicly observable competitor pricing and consumer demand patterns. Full transparency at every step.

Fairness Built on Data, Not Assumptions
Humans have biases. We favor certain days, times and weather conditions. We make assumptions based on gut feel.

Properly designed AI can assist in making fairer, more robust pricing choices because it works from data, not emotion. It’s a superpower for consistency because it uses the same rigorous analysis, applied the same way, every time.

But it only operates within the boundaries you define. The pricing manager sets the strategy, goals, and constraints. Fair pricing isn’t about removing human judgment. It’s about enhancing it with unbiased analysis.

Security Is Built In, Not Bolted On
Security is built into every layer of A2i PriceCast.

• Encryption — your data is protected in transit and at rest
• Access controls — you decide who sees what
• Audit trails — every access, every change, tracked and logged
• Data rights — request deletion at any time, no delays

Accountability Stays with You

Humans remain accountable and that’s by design.
The AI suggests, you decide. The AI analyzes, you approve. The AI learns from your data, and you teach it the rules. You’re in the driver’s seat by setting the strategy, reviewing the recommendations and making the final call. The superpower is yours and so is the accountability.

Why This Matters
When AI touches your pricing, principles aren’t optional. They’re essential.

It’s not about having the smartest AI. It’s about having AI that:

• Respects your expertise
• Protects your data
• Explains itself
• Keeps you in control

Every transaction makes it smarter. Every price change teaches it something new.

The New Reality: When Markets Move Before You Do
A pipeline explodes in Eastern Europe. Oil futures spike. Your competitor drops prices. Three stations down the road raise theirs. If your response depends on a spreadsheet and a phone call, the market has already moved again.

This is why we built A2i PriceCast — an AI-driven fuel pricing system that learns from every gallon sold and delivers the recommendations you need to stay ahead. Think of it as a superpower for your pricing team.

How PriceCast Works: Six Steps, You in the Middle
A2i PriceCast is built around a continuous learning loop.

Step 1: It studies your history. Historical data teaches the AI what worked, what didn’t and why.
Step 2: It integrates live data. Every transaction flows directly from your point-of-sale (POS) systems. No delays. No snapshots. Real-time data feeds the model continuously.
Step 3: It identifies patterns. The Tuesday afternoon surge. The weekend dip. It analyzes customer behavior patterns and forecasts what’s coming next.
Step 4: You set the rules. This is where human strategy enters the algorithm. You define the targets — volume, margin, market share. You set the boundaries. The AI works within your strategy, not around it.
Step 5: It delivers a recommendation. A suggested price, with optimal timing, backed by the data. Ready for your review and approval.
Step 6: It learns from every sale. With every new transaction, the cycle starts again. Tomorrow’s recommendations are sharper than today’s.

Why This Learning Loop Matters
1. Real-Time Responsiveness
The Old Way: In the past, teams relied on manual pricing updates paired with static weekly reviews.
The Problem: This approach fails because modern markets shift hourly, rendering weekly adjustments obsolete before they are even implemented.

2. Data-Driven Independence
The Old Way: Most businesses simply matched the competitor across the street’s prices.
The Problem: This is a risky gamble because your competitors might be basing their prices on incomplete data or flawed logic.

3. Contextual Agility
The Old Way: Strategy was often dictated by recycling last year’s playbook.
The Problem: This method is ineffective today because last year’s market conditions and consumer behaviors no longer apply to the current economic landscape.

With A2i PriceCast, AI analyzes in real time and delivers a recommendation before your morning call. You make informed decisions faster — and with better data. That’s the superpower: not replacing your expertise, but amplifying it.

When Geopolitics Hits the Pump
Today’s fuel market isn’t just about local competition. When sanctions hit, supply chains break, or shipping lanes close, prices move fast. A2i PriceCast recalculates. Based on your transaction data, publicly observable competitor pricing and current market conditions, it delivers updated recommendations so you can respond with clarity — not guesswork.

The A2i PriceCast system:

• Surfaces relevant signals from the data as conditions change

• Delivers updated pricing recommendations

• Gives you the insight to protect margin during volatility

You review. You approve. You stay in control.

What Powers Every Recommendation
A2i PriceCast is backed by:

• OPIS market data spanning decades of fuel pricing history

• AI that improves with every transaction from your stations

• Your local knowledge built into the system through the strategy and rules you define

You Stay in Control — With Superpowers

A2i PriceCast handles the analysis — studying transaction data, identifying demand patterns and forecasting consumer behavior. It gives your pricing team capabilities that simply aren’t possible with manual methods. But the final call is always yours.

A2i PriceCast’s AI:

• Analyzes — you focus on strategy

• Surfaces opportunities — you decide which to pursue

• Processes the data — you apply the insights

• Recommends — you approve before anything changes

The philosophy isn’t to replace the pricing manager. It’s to give them superpowers.

Our Five AI principles ensure guardrails are built into every layer of A2i PriceCast:

Human Control and Oversight — You set the goals, define the restrictions, and approve every pricing decision. The AI operates within the guardrails you provide.

Data Ownership and Integrity — Your data belongs to you. It is siloed and never used to train another retailer’s model. Our AI algorithms are trained with data from only one customer at a time — your commercially sensitive information is never used to make recommendations to other customers.

Transparency and Explainability — We tell you which data trains the model and explain how the algorithm reaches its recommendations.

Fairness and Robustness — Properly designed AI assists humans in making fairer, more robust pricing choices — free from the biases inherent in manual decision-making.

Privacy and Accountability — AI algorithms must be secure and prioritize privacy and data rights. People are accountable for their decisions — PriceCast is built to keep it that way.

The Bottom Line
In today’s volatile market, relying on yesterday’s pricing methods often means leaving margin on the table.

Operating without data-driven insights creates a strategic gap where others are:

• Engaging price-sensitive customers with more tailored offers.

• Optimizing margins by acting on granular data.

• Identifying and learning from emerging market patterns.

AI’s superpower is it’s ability to recognise patterns. Detecting anomalies plays a vital role in identifying deviations from what is considered ‘normal’. Anomalies can provide crucial insights into potential issues, exceptional events, or outliers within metrics. In this example we explain how we were able to apply AI to help a customer who was experiencing payment terminal malfunctions with certain payment methods.

Know the data

The first step of the process is to know your data. The chart below shows transactions over a set period for certain payment types, with each colour representing a different form of payment. To the naked eye, it’s quite obvious that payment type 1 (orange), 9 (purple) and 14 (brown) have an outage and that 19 (pink) has been dead for a while. What might get overlooked is payment type 0 (blue) which appears to work sporadically. What is clear, is that since March 5th transaction patterns have significantly changed. 

Stats will get you some of the way

To better understand what is happening with the transactions we applied PersistAD. PersistAD identifies anomalies that persist across consecutive windows. The chart shows transactions across a 24 hour period. Whilst the system was able to detect some anomalies, it was not able to detect the complete change in transaction patterns from March 5th onward. This method also requires some fiddling on a site-by-site level. Transaction patterns on smaller sites, for example, will deviate quite significantly from larger sites as there may be be longer periods without any transactions.

Autoencoders

The next step was to try an autoencoder to detect anomalies in the data. An autoencoder is a type of neural network architecture designed to efficiently compress (encode) input data down to its essential features, then reconstruct (decode) the original input from this compressed representation.

Autoencoders, like large language models (LLMs), rely on neural networks to achieve their amazing capabilities and come in a range of different configurations depending on the task you want too solve. They are often trained using unsupervised learning, which means there is no labelling of the training data, to discover hidden relationships in the input data.

Aside from anomaly detection, autoencoders can also be used for a number of other applications:

To detect anomalies in the transaction data both the encoder and decoder were configured as one dimensional Convolutional Neural Networks and we used unsupervised training on a ‘normal’ part of the data. 

Convolutional Neural Networks are the corner stone of Deep Learning – they are excellent at learning patterns and then generating their own similar patterns. Deep fakes, false images that have been digitally altered to appear real, are a perfect example of this. The technology uses Convolutional Neural Networks to learn patterns, for example a famous person’s face, and then uses this to generate similar patterns resulting in new images.

The Autoencoder dynamically learns from patterns in the data and when applying this we were able to recognise whenever payment transactions looked odd. [Imagine example above]

Fine tuning

Even though we found a solution to the customer’s problem using the autoencoder, we still needed to maximise the performance of the AI much like tuning the aero dynamics of an F1 car from track to track. 

The Problem:

Create an easy-to-use app where our customers can take photos of competitor price signs and send the data directly into the PriceCast pricing solution.

The Approach:

1. Define inputs and outputs

The input in this instance is the photo of the price sign and the GPS coordinates of where the photo was taken (a request from the customer) with the output being the prices on the sign.

2. Collecting the data

When it came to training the AI, we didn’t have a database of hundreds of photos of price signs we could train it on. In fact, we had none from the region where our customers are based. So, we started collecting data. We asked our customers to send us lots of photos of price signs. These images were taken at different zoom levels, in different weather and at different times of day.

3. The AI Model

AI Vision frameworks such as Microsoft’s Azure Vision are designed to extract meaningful information from digital images. Using the cloud-based Azure system, plus some pre-processing and post-processing work to correct the prices Azure returned, we were able to recognise 96% of prices on the images our customers sent in.

In total it took us around two days to build the proof-of-concept algorithm, including some fine tuning.

4. The outcome

The Price Capture app, now available on the App Store and Google Store, helps retailers to simply and efficiently build on a database of competitor prices.

Latest acquisition advances Dow Jones’s energy business with industry-leading artificial intelligence (AI) capabilities 

Dow Jones announced that it has acquired A2i Systems, a world leader in AI-powered fuel pricing solutions. 

A2i adds to Dow Jones’s growing suite of AI capabilities and will operate as a subsidiary of OPIS within Dow Jones’s energy business, maintaining its focus on innovation and product development. A2i’s best-in-class AI engine applies advanced predictive technologies and real-time pricing data to forecast consumer buying behaviors in dynamic market conditions. Its PriceCast platform is in operation at over 12,500 fuel sites, electric vehicle (EV) charging stations and convenience stores across 20+ countries globally.

A2i joins Dow Jones at a time of continued growth and expansion as a leading business news and information business. In its latest reported earnings, Dow Jones revenues totaled $544 million, which included 15% growth in its energy business.

Headquartered in Odense, Denmark, A2i has a strong track record of growth and a broad geographical footprint across Europe and North America. With this acquisition, OPIS will substantially diversify and strengthen its suite of offerings for retail customers, where market demand for pricing, analysis and forecasting is growing rapidly.

“The business and teams we are welcoming to our company today have built one of the most trusted, ethically sound AI platforms in the industry,” said Almar Latour, CEO of Dow Jones. “This knowledge and expertise is an excellent companion to OPIS, enabling us to create immediate value for our customers and subscribers. Our shared commitment to integrity and innovation with AI open a range of growth opportunities not only for our energy vertical but for Dow Jones writ large.”

“We’re thrilled to welcome A2i to our team,” added Brian Crotty, general manager of Dow Jones’s energy business. “Since 2007, A2i has been a pioneer in applying leading-edge technologies to optimize fuel pricing strategies. This move will strengthen our position within the evolving retail sector, helping our customers tap into the booming EV market and navigate their transition from traditional fuel-first forecourts into multi-purpose mobility hubs.”

Frodi Hammer, A2i founder and CEO added: “Joining forces with OPIS, a brand that is trusted across the fuel supply chain for its market-leading news, data and analysis, presents an amazing opportunity to scale our technology and impact. Today marks the start of an exciting new chapter and we are confident that the team will flourish as part of OPIS and the wider Dow Jones organization and continue pushing forward with innovation.”

About Dow Jones

Dow Jones is a global provider of news and business information, delivering content to consumers and organizations around the world across multiple formats, including print, digital, mobile and live events. Dow Jones has produced unrivaled quality content for more than 130 years and today has one of the world’s largest news-gathering operations globally. It is home to leading publications and products including the flagship Wall Street Journal, America’s largest newspaper by paid circulation; Barron’s, MarketWatch, Mansion Global, Financial News, Investor’s Business Daily, Factiva, Dow Jones Risk & Compliance, Dow Jones Newswires, OPIS and Chemical Market Analytics. Dow Jones is a division of News Corp (Nasdaq: NWS, NWSA; ASX: NWS, NWSLV).

About OPIS

OPIS, a Dow Jones company, provides accurate pricing, real-time news and expert analysis across the global fuel supply chain, including the Spot, Wholesale Rack and Retail markets. OPIS and its brands, McCloskey, PetroChem Wire, Axxis and Chemical Market Analytics, enable customers to buy and sell energy commodities with confidence across the globe via easy access to transparent data, expert-level customer support, educational events and energy data solutions.

OPIS assessments reflect confirmed bids, offers and trades reported by approved traders, brokers and electronic platforms. Full details about OPIS pricing methodologies are available at opisnet.com/about/methodology.

As forecourts evolve away from the traditional fuel first model towards multi-purpose mobility hubs that offer a range of charging, retail and additional services, our solutions must evolve with them. For over 15 years A2i Systems has provided artificial intelligent fuel pricing solutions to retailers across the globe. PriceCast Fuel uses a range of data streams such as customer 

purchasing behaviours, weather, local events, oil price and global incidents to proactively price fuel products ensuring retailers can meet their business objectives even in volatile markets

The algorithm behind PriceCast was first developed as a way to identify and analyse the behavioural habits of children on the playground as a means of reducing childhood obesity. Our founders soon discovered they had created a neural-net based self-learning AI engine capable of so much more. Now as the fuel and convenience retail industry continues to evolve, so does PriceCast in the form of PriceCast EV and PriceCast C-Store.

PRICECAST EV – COMING SOON!

The electric vehicle market is booming. Last year, almost 2 million new electric cars were registered in Europe and with more affordable EVs on the horizon it is expected that the market will continue to grow. With more EVs on the road, we have also seen an increase in charging services, not only from traditional fuel retailers, but new players entering the market from outside the mobility industry. With increased competition and a whole range of factors that effect the price of charging, we are now seeing a market primed for predictive pricing.

The price of electricity, type of charging station, location, network memberships, time-based vs energy-based charging, fluctuations in demand, season, time of day, additional onsite services and government incentives can all effect the price of charging your EV. Whilst these differ from the factors that impact the pricing of traditional fuels, the concept remains the same. By considering all available data, artificial intelligence is able to price proactively. In fact, one key advantage to pricing electricity over traditional fuels is the availability of data. At any given site you can see not only the cost of electricity but the availability of chargers through a number of readily available apps.

Whilst dynamic pricing has obvious benefits for the retailer, it does not consider all the factors that can influence pricing. Predictive pricing using artificial intelligence takes pricing to the next level. By focusing on customer behaviours as well as the factors outlined above, artificial intelligence can spot trends and adjust the prices accordingly.

PRICECAST C-STORES – COMING SOON!

What if you could price the products in your store in the same way as you price your fuel or electricity? What if you could build a better understanding of your customers’ purchasing behaviours and reward their loyalty with timely, relevant offers delivered at the optimal time. This is where PriceCast C-Store comes in.

With demand for fuel predicted to decline and electric vehicles becoming increasingly popular, the c-store must become a destination in its own right. By building a better understanding of the customers that visit their store, their purchasing behaviours and their needs retailers can create offers that are relevant to the customer and find ways to attract them in store. As with PriceCast Fuel and EV the AI can examine a whole range of factors that can impact product pricing and make recommendations to help retailers to meet their business goals.

The European EV market is booming. Last year almost 2 million new electric cars were registered [European Environment Agency] and with more affordable EVs on the horizon it is expected that the market will continue to grow. For a long time the fuel retail industry has played a chicken and egg game with car manufacturers, trying to strike the perfect balance between serving the emerging electric vehicle market and offering services that remain profitable. Now, with an increase in demand for EV charging, it is not just traditional fuel retailers entering the charging game, but new competitors from outside the mobility industry.

The EV charging market still has room for growth, but with increased competition and a number of other factors that effect the price of charging we are starting to see a market primed for predictive pricing. So what effects EV pricing?

Unsurprisingly, the cost of electricity is a key determinant of charging cost however the type of charging station, location, network memberships, time-based vs energy-based charging, fluctuations in demand, season, time of day, additional onsite services and government incentives can all impact pricing.

Whilst some of these factors differ from those that impact traditional fuels, the principle is still the same. By considering all available data, artificial intelligence is able to price proactively. In fact, one key advantage to pricing electricity over traditional fuels is the availability of data. At any given site you can see not only the cost of electricity but the availability of chargers through a number of readily available apps.

Those accustomed to charging, whether at home or on the road, will know that dynamic pricing is already in place for the majority of charging providers. As the price of electricity fluctuates throughout the day, the prices adjust accordingly. This is why many people will choose to charge their car overnight when electricity is cheaper. Whilst dynamic pricing has obvious benefits for the retailer, it does not consider all the factors that can influence pricing. Predictive pricing using artificial intelligence takes pricing to the next level. By focusing on customer behaviours as well as the factors outlined above, artificial intelligence can spot trends and adjust the prices accordingly. For 16 years A2i has been pricing traditional fuels in this way, helping retailers to achieve their goals in volatile markets.

Convenience trumps price

One key difference between pricing electric charging and traditional fuels is the time it takes to recharge. If a fuel station is full the queues are likely to move quickly, however this isn’t the case with EV and customers will often settle for paying more if the charging experience is more timely and convenient. If, for example, you operate a site that is currently empty and your competitor across the street is 95% full, reducing your price may not be the right thing to do. This example perfectly illustrates the potential margin EV operators can gain by having the right price for their EV charging at the right time.

The additional wait time can also influence where and when customers choose to charge. A strong convenience offering where a customer can pick up groceries for dinner or a cafe with good coffee and reliable wi-fi where they can work can also factor into the decision making process. Customers may also choose to build their charging time around other tasks such as food shopping, or during their working hours. Only with customer-centric pricing can retailers spot behavioural trends and use this to inform their pricing strategy.

Charging doesn’t need to be complicated

One key advantage to owning an electric vehicle is the ability to charge at home. However this isn’t always an option and, particularly for longer trips, the fast charging network is essential. Some homes are unable to install chargers due to the location or because of increased pressure on the electricity grid. Even if a customer is charging at home, this electricity will still be provided by someone and they too could benefit from predictive pricing. We are seeing more and more energy providers entering the charging arena providing both at home charging and access to certain networks on the go often through subscription type models.

Subscription models have been a popular method of packaging charging services, however critics have stated that often these methods lack transparency and customers are not always aware of the true cost of charging their vehicle. Complex pricing structures, hidden fees, inconsistent pricing and limited access to real time pricing information all hinder the experience of customers. By harnessing the power of artificial intelligence, retailers can better understand their customer needs and provide them with transparent pricing information wherever they choose to charge their vehicle.

Charging plus…

As electric vehicles continue to take off and the market becomes more competitive, we recognise not only the importance of predictive pricing for EV chargers but how PriceCast technology could also be used for convenience and additional services. Our roadmap is focused on providing artificial intelligent technology to support retailer’s goals whichever direction the industry might take.

A2i Systems (A2i), an artificial intelligence fuel pricing company, announced today it has signed a reseller agreement for PriceCast Fuel with Invenco by GVR, a Vontier company and global leader in innovative technology for convenience stores, retail and commercial fueling solutions and services.

PriceCast Fuel by A2i is an artificial intelligence fuel pricing solution designed for today’s ever-changing market. The self-learning AI technology is able to identify and predict consumer trends, empowering organizations to make better decisions and maintain a pro-active pricing strategy, even in volatile market conditions. 

Under the agreement, the partnership will initially focus on European markets where Invenco by GVR will offer PriceCast Fuel for both existing and new accounts. The companies are also working to ensure full compatibility with Invenco by GVR’s iNFX solution, a cloud-managed platform of microservices that makes it easier to bring new capabilities and features to market faster.

Frodi Hammer, CEO and Founder at A2i said: “PriceCast Fuel goes hand-in-hand with Invenco by GVR’s vision and roadmap to redefine convenience together. Their laser focus on helping retailers adapt and stay ahead by producing agile solutions and supporting innovative products like PriceCast Fuel is exactly what the industry needs and we are extremely excited to see how this develops over the coming years.”

“A partnership with A2i is truly exciting,” says Dennis Larsson, Retail Solutions Director for Europe at Invenco by GVR. “The added value for our cloud offering will translate into instant performance gains for customers, while supporting our long-term growth strategy in composable retail.”

A2i and Invenco by GVR will jointly exhibit at Oil&NonOil in Verona, Italy from 29 November to 1 December. To find out more about PriceCast Fuel visit booth C24.

Artificial intelligence pricing experts, A2i Systems (A2i) has launched a brand new mobile phone application, Price Capture, which allows users to easily capture data from price signs with a click of a button.

Users can simply use their smart phone camera to take a picture of a price sign, feeding the data directly into their system without the need for manual price entry. The app, which is already in use in Europe, is an ideal solution for locations where the data feeds are not as strong or for retail networks that would prefer to generate their own data feed.

Once the data is fed into the system this can then be used to make data-driven pricing decisions, whether using artificial intelligent pricing or not. For retailers implementing PriceCast FueI, the competitor data, alongside transactional and traffic data, can be used to predict emerging customer behaviours. AI models correlate incomplete and noisy data streams to make the data actionable, meaning retailers can then prompt the system for an optimal pricing strategy. Depending on the stage of AI adoption, retailers can either use the information to qualify their decision making, ask the AI to come up with a solution or, for fully autonomous users, the AI will take the decision itself.

This was A2i’s second year at the NACS Show and, CEO and Founder Frodi Hammer noticed a shift in the attitudes towards artificial intelligence in the past year, he said: “More and more retailers are aware that they need to be using AI. Thanks to ChatGPT, people have seen that AI isn’t scary but a useful tool that can support business. Last year we had a lot of interest from larger networks but we are really starting to see smaller retail networks recognise the benefits of AI and how it can help them to automate their systems and processes.”

A2i’s PriceCast Fuel customers will also now benefit from the next-generation Dashboard 4. The new dashboard was built from the ground up working alongside existing customers. The result is a user-friendly, customisable dashboard that allows users to run several work flows seamlessly. The modular set-up allows users to configure the dashboard to suit the way they work.

“Dashboard 4 is a complete rebuilding of the dashboard. We listened to our customers and worked with them to create a system that works for them. The dashboard can be tailored to the customer and we have followed best practices throughout to create a great user experience,” added Frodi.