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.

As the Greek philosopher Heraclitus famously wrote: “The only constant in life is change.” But whilst the world around us is constantly changing, humans are creatures of habit. We like to build routines doing the same things, at the same time; day after day, week after week. Change can be hard. It disrupts our daily life and has the potential to thrust us into new and unexpected directions.

Over the last half century technology has grown exponentially and has vastly altered the way we live and work. To put this in to context, a modern smartphone is more powerful than the guidance computer NASA used for the famous Apollo 11 mission. In 53 years we’ve managed to condense technology that once filled an entire room in a government-controlled building into something that fits into the palm of your hand and is accessible to everyone. With all this technology at our fingertips, businesses have had to altered the way they work to remain competitive in today’s digital first world. Whilst these changes are necessary for success, they do require change management processes. According to McKinsey 70 percent of change programs fail to achieve their goals, largely due to employee resistance and lack of management support (LINK)

To ensure change is successful, management teams need to make the process as painless as possible.

When change is first suggested, most people want to know three things:

• What does this change mean to me?
• Why is it happening?
• What will it look like when the change has been made?

The answers to these questions help them to assess the level of risk and difficulty involved in the change. At this stage most humans see change as a threat, viewing it as difficult (not knowing how to do it or thinking people could make it hard for them), costly (taking from them things they value such as time, money or status) and weird (a change to the status quo).

The reason many change management processes fail is that people become stuck in this mindset. To embrace change, people need to recognise that the change could be easy or at least achievable, that the pros to the change will outweigh the cost and that change could become the new normal.

So, how can we help people to make this shift?

Increase understanding

It is impossible to instigate change without providing foundational information about the change.

What is it?

Why is it happening?

Why will this lead to a better future?

PriceCast Fuel is a software that is driven by artificial intelligence. AI is often perceived as a threat, whether as the antagonist in a sci-fi movie or as a technology that will render you jobless. With this in mind, simply telling your pricing team that you are switching to an AI pricing solution without any context or further explanation, no matter how positive the delivery, will not give them the key information they need.

PriceCast Fuel provides real-time insights, data-driven pricing strategies, and enhanced operational efficiency powered by artificial intelligence. It learns and identifies customer trends and empowers you with predictive, customer-centric insights that ensures the right price, to the right customer at the right time.

As demand for traditional fuels declines, a data-driven approach to fuel pricing is more critical than ever. PriceCast Fuel has helped retailers across the world to maintain a pro-active pricing strategy, even in volatile marketing conditions. The self-learning AI technology is able to identify and predict consumer trends, empowering organisations to make better decisions and become more strategic.

PriceCast Fuel is designed to support the work of the pricing team, not replace them. PriceCast Fuel can eliminate tedious work, highlight sites that require attention and offer an opinion on how to solve it. It is this ability to devise a solution and cooperate with the pricing analyst that sets an AI solution apart from a simple expert system.

Of course, your teams are likely to have further questions and it is essential that you are able to answer them. By providing honest, realistic information and building a strong case for change this will help people to start to shift towards a more positive or neutral point of view.

Clarify and reinforce priorities

Letting people know what isn’t changing can be just as important as letting them know what is changing. As mentioned PriceCast Fuel is designed to support the work of the pricing team, not replace it. Understanding that their roles will remain largely the same will help to reassure them.

Give control

The team will need to build trust in PriceCast Fuel, this can be achieved by understanding how the AI system works and being able to explain how and why it has come to a decision. AI can be integrated in three stages – assisted, augmented and autonomous. This phased approach helps teams to adjust to the changes step by step.

The AI acts as a digital twin so retailers can test simulations and ideas, for example they can see how a price increase would affect the volume and margin at a site and how the market would react to the change. By being able to play around with these ideas teams can become more familiar with the AI and build trust in the process. This a vital step in the AI journey as it prepares businesses and their teams for fully autonomous AI.

Give support

It’s important to remember that change takes time. Throughout the process it is essential to provide consistent support. Questions need to be answered as they arise and people need time to adjust. Instead of viewing any concerns as resistance, try to understand the worries of your team and respond in a thoughtful way.  If people feel they are being heard and their issues addressed, they are less likely to remain stuck in a negative mindset.

As part of the PriceCast Fuel subscription, customers can benefit from A2i’s performance development service. The service is designed to help customers seamlessly transition from their old way of pricing to PriceCast Fuel in a phased approach. The process starts by helping retailers to price in the way they usually do using PriceCast Fuel. The second step is to start using artificial intelligence in restricted mode and the final step is using advanced AI in non-restricted mode. This helps customers to gradually build trust in the system.

When implementing PriceCast Fuel we work closely with the pricing teams to ensure the process is as smooth as possible and we can address any concerns that may arise. Even after the initial set-up phase we continue to offer PriceCast Fuel customers 24/7 support from our centre based in Denmark.

Whilst change is inevitable, it is essential to remain patient. Fear, hesitation and resistance are totally normal responses to change but shifts can happen with the right support and processes in place.

Artificial intelligence. In today’s world it’s impossible to escape it. What was once considered a futuristic concept from a dystopian future is now embedded across all areas of our lives. Businesses are increasingly turning to AI – carefully weaving together strategy, process redesign, and human and technical capabilities to drive their business forward.

On the forecourt artificial intelligence can be used in a variety of different ways and can help retailers gain a competitive edge. To successfully fuel a business with AI however, retailers must challenge their processes and adopt a holistic approach where they not only recognise how AI can drive business outcomes but have the ability to create a culture that supports and harnesses the capabilities of artificial intelligence.

The road to AI

Becoming an AI-fuelled business isn’t like flicking on a light switch. It is a journey that requires reimagining processes, deploying AI in the right areas and change management. It is important to recognise that artificial intelligence is an important tool to support your business, not to dictate how you should do business. Staff will need to build trust in the system and realise that the AI is there to enhance their capabilities, not replace them. Part of that process is understanding how the AI system works and being able to explain how and why it has come to a decision. 

A2i’s AI-driven pricing solutions are configured to the objectives and goals of each individual customer.  AI can be integrated in three stages – assisted, augmented and autonomous. The AI assists by managing vast amounts of data collected by the business and augments by augmenting human analytical competencies. The artificial intelligence supports retailers in their work and decision making. By acting as a digital twin retailers can test simulations and ideas, for example they can see how a price increase would affect the volume and margin at a site and how the market would react to the change. By being able to play around with these ideas teams can become more familiar with the AI and build trust in the process. This a vital step in the AI journey as it prepares businesses for stage three – autonomous AI.

Autonomous AI is able to take action without human intervention and this is where businesses can gain a real advantage over the competition. With this type of self learning technology it is essential that the models are consistent and don’t change, but rather adapt to the conditions. This is something that must be carefully considered when designing the AI. If done correctly, this will result in a AI system that is more robust than traditional statistical models as it is capable of finding solutions outside its specified domain values.

Humans and AI

Artificial intelligence will not replace humans but humans with AI will replace those without. Rather than thinking of AI as something that will replace the human workforce, businesses need to rethink the human-machine interaction entirely. AI is a powerful tool that can support decision making, increase productivity and free up humans to take on other roles. To become an AI-fueled entity, businesses must find ways for machines and humans to work together in digitally designed processes.  

For pricing teams, an AI solution like PriceCast Fuel can eliminate tedious work, highlight sites that require attention and offer an opinion on how to solve it. It is this ability to devise a solution and cooperate with the pricing analyst that sets an AI solution apart from a simple expert system.

Supporting you on your journey

The journey to becoming an AI-fuelled organisation may seem daunting, but in reality it is just the latest technological advancement on the road to increased productivity and strategic possibilities. To take this step effectively businesses can phase in the integration of AI and build new process and systems that emphasise the collaboration between humans and machines. But, businesses don’t have to go it alone. Supporting businesses through the change management process is just as important as providing the solutions. At A2i Systems we work with our customers to help them navigate this path.

The AI chatbot has multiple functions including answering questions in a human-like way, composing essays, describing art in great detail, creating AI art prompts and can even engage in philosophical conversations.

With AI now becoming a part of daily life this opens up a wealth of opportunities for businesses, but also a set of new challenges.

To showcase the capabilities of AI, I asked ChatGPT to come up with a song that summarised the key points in each section.

To first understand how AI can revolutionise convenience retailing, we must first understand the current market landscape.

“…the lyrics don’t directly reference AI and the convenience retail industry, the message is of overcoming challenges and coming out stronger on the other side…”

The predictions will come as little surprise to fuel and convenience retailers. EV and hydrogen cars are gaining popularity, governments are legislating to support the transition away from fossil fuels and forecourts all over the world are evolving with an increased focus on convenience.

Beyond the forecourt the world has never been as volatile as it is right now. COVID-19 and the war in Ukraine have created volatility and economic uncertainty. Combine this with wavering oil demand, increased EV adoption, the rise of carbon neutral fuels and consolidation of fuel retailers and the landscape can look a little crazy.

“…society is constantly evolving and change is inevitable…it reflects the idea that AI has the potential to revolutionise the convenience retail industry, but ethical and societal implications must be addressed.”

One of the key issues we are facing with technologies like deep learning and, to a certain degree, generative AI (like ChatGPT) is that we can’t explain how it came up with the solution it did.

From a business perspective being able to explain how the AI has come to a solution is essential in the change management process. By building AI models on smaller data sets this allows us to improve the decision making of the AI and enhances the autonomy in AI systems. Here is an example of how AI based fuel pricing works:

In this example of an AI model from PriceCast Fuel you can calculate the price elasticity of the supply and demand on station product level down to the minute. Like with generative AI, the AI is trained on samples, however these samples are engineered to keep their semantics such that the end user can gain an understanding of the reasoning behind the decision-making.

When the AI can start to explain how and why it is acting the way it is, it becomes more powerful.

“The song speaks to the idea of change and a new way of doing things, which is relevant to the potential of AI in the retail industry for implementing AI in their businesses.”

We know that we will need AI and we also know that first movers have the possibility of winner takes most, so how do we get real about implementing AI in our business?

Start with a clear focus on how to operationalise AI. With PriceCast Fuel the AI is capable of deciding on the individual prices of products, removing the responsibility and tedious tactical work of having pricing analysts set up various rules and defining distance to competitors.

There is no simple way to implement AI in an organisation. AI is a powerful tool capable of seeing multi-dimensional correlations. Having selected the right AI model we get superhuman capabilities and this can be hard to implement. Change management is critical for us when introducing PriceCast Fuel. We often start migrating the current pricing set-up as it stands and involve pricing analysts in the process.

Start small and be focused. Measure the effect of the AI and make sure it fulfils its purpose of delivering a compelling customer experience and results in the expected business outcome. With PriceCast Fuel, we do this by constraining the AI around business rules so that the pricing analysts can control the introduction of AI into the pricing step-by-step – allowing them to approve any price suggestions within familiar KPI’s.

By leveraging AI you can extract footfall data from your regular IP cameras. This allows you to trace the customer’s movements throughout the site. Is the person plugging in their EV car also going into the shop as well? Where in the shop? Is there dwell time anywhere?

Suddenly your video feed has become actionable data from which you, or another system can take decisions.

AI could also be used to create store planograms or even to price products in store based on inventory and ensure benchmark products are priced correctly.

Most importantly, AI can help you understand how, when and why customers engage with your business. Social media likes aren’t enough anymore – you need to understand the intention of each and every customer on your forecourt. When you know that, you can transform this knowledge into business actions, which in turn will help deliver a compelling customer experience.

KEY TAKEAWAYS

• A Gloria Gaynor said “ I will survive” but to do so you must view volatility as an opportunity.

• The time’s are a-changin’ – AI is already shaping the future.

• Revolution – what can AI accomplish for you by making your data actionable?