How We Find AI Use Cases

Our process is based on helping > 50 businesses decide what to do with AI

Machine learning is an extremely versatile tool. Some applications are very public, like Netflix’s Movie Recommender or Google Translate. Many more are hidden, built behind the scenes by teams that used AI to solve some unique challenge for their business.

If your business has a large amount of data and you’re asking yourself, “How can I use AI to build something smart from our data?” — keep reading. We’ve helped many businesses answer this question. This is our process:

1. Set up a meeting with the right people

2. Introduce everyone to machine learning

3. Absorb everything, assume little

4. Make a list of processes ripe for machine learning

5. Check feasibility

6. Prioritise

7. Research

8. Make a decision

1. Set up a meeting with the right people

Whatever use case you discover has to be rooted in company goals and data. Neither management nor engineering can give you all the answers. You need a cross-disciplinary meeting. Have a meeting with a product visionary (CEO, VP Product) and someone who knows every dataset (CTO, Head of Data Engineering). You should plan at least half a day for this.

You need a cross-disciplinary meeting.

2. Introduce everyone to machine learning

Machine learning is a tool like any other: the more you understand it, the better you can put it to use. If people think it’s a magical black box, then they won’t be able to help you with your search.

So make it practical, leave out the math, and cover these three basics about machine learning:

  1. What is machine learning?
  2. When can you use it?
  3. What are the common misconceptions?
I’ve written a post to answer these questions: The 3 Basics of Machine Learning

Once everyone has an understanding of what machine learning is, it’s time for you to learn from them:

3. Absorb everything, assume little

Every firm is unique. Even within narrow verticals, the overlap in what two different companies need is smaller than you might think. Don’t try to fit your business into a box.

Map the terrain

Map the business terrain.

Goals. What goals are driving the company right now? What are the challenges behind these goals?

History. What projects have been implemented in the past? What were the results, the challenges, and the lessons?

Data. What data exists? Where is it generated, and where is it saved? How much consistent history is there in each database? How exactly does each table look? Can the different datasets be merged on unique identifiers?

Infrastructure. What is the preferred infrastructure? Are there relevant policies or restrictions on which provider to use (on-premises, AWS, or Google Cloud)?

Data Science Strategy. What is your data science vision? Do you want to build up your own expert team, or do you want to find an experienced team to build you a solution? Or a combination of both?

After you know what’s driving your business at the moment, you can get more concrete. Now it’s time to collect all the potential use cases.

4. Make a list of processes ripe for machine learning

Where is a lot of data being used to automate decision making?

Machine learning is just a tool to automate pattern discovery and then make smart predictions based on those patterns. Most of the time it’s about improving an existing process by making it a little bit smarter. Processes that are good candidates for machine learning are usually:

Data based: Decision-making in the process is already entirely based on data.

Large scale: Decision-making happens over and over again, thousands or millions of times.

Automated: The process already uses software to some degree.

Already automated, large-scale, data-based decision-making processes are the perfect potential candidates for machine learning systems.

Good examples:

  • Product recommendations
  • Credit scoring
  • Personalised marketing
  • Fraud detection
  • Image recognition

So think about where a lot of data is being used to automate decision making, and whether there is room for improvement.

The next best place to use machine learning is to support a process that’s currently done by people. If it’s entirely data based, highly repetitive, tedious, and therefore slow, it might be ripe for improvement. Can you make it faster by training a machine to take on some of these decisions?

5. Check feasibility

For each use case, find out whether the necessary data is being captured. Specifically, check whether the different datasets you need can be merged.

The more machine learning projects you’ve already implemented, the better you can pinpoint the right questions to ask. Build on your previous experience:

  • What are the common pitfalls in projects like this one?
  • Which datasets are the most important to have, and which ones are optional?
  • What is a reasonable level of improvement to expect in this situation?

If you haven’t implemented a similar use case before, talk to a team that has.

6. Prioritise

Prune ideas early if they aren’t helping achieve the company’s most important priorities. Refocus the discussion: “This is more of a nice-to-have, so let’s leave it for now.”

Ask critical questions: “If we did manage to automate and improve the accuracy or speed of this process by 20%, what would that mean in revenue per year?”

To compare the cases you have left, make an Excel spreadsheet with the following columns:

Data availability — How easy is it to access the right data for this application? If you don’t have the data yet, give it a very low rating.

Potential gain — If things go very well, how big is the potential impact on a critical business priority?

Risk — Are there many unknown factors that could derail the project? What does your experience tell you?

Time to implement — Prioritise quick wins. With one solid success behind you, you can move on to the more complex projects.

7. Research

Once you’ve identified your top 1–3 cases, do a broad search through Google:

  • Who has implemented similar systems before?
  • What approaches did they try? Which ones did they settle on and why?
  • What were the learnings and the final results?

In machine learning, you can patch together some of that information from published academic research. Don’t copy their approach, though. It’s likely that it was just good for their specific dataset. Get inspired, and steal the best ideas. Use them to guide your further investigations.

Another good source is Kaggle competitions. If you find a competition for a similar use case, look at the kernels and the forum discussions. They will give very specific input on how to implement and tune an algorithm, and in most cases you can even find full sample code.

8. Make a decision

Update your use case ranking with the additional information you learned. Then, based on your research and experience, make a rough project plan for each idea.

Together with your prioritization table and the project plans, present your findings to your team.

If you’ve done this, always keeping the bigger goals in mind, it should now be easy for your team to decide on the best project.

Time to get your hands dirty and implement.

Have fun!

Energy Transmission

Anticipating and Preventing Power Grid Failure

Massive power outages cause chaos for the general public, and they cost utility providers roughly $49 billion a year.

This wouldn’t be much of a problem if massive power outages were rare, but outages affecting more than 50,000 people have increased dramatically in recent years. This means utility companies need to find new ways of anticipating and managing these outages.

These days, smart grids are producing massive amounts of data, which means predicting and managing outages is easier than ever. Unlike traditional power grids, which are one-directional (meaning they only transmit power in one direction), smart grids are two-directional. They can capture data from every possible source in the grid at the same time as they’re providing electricity. They collect and monitor data from sources like smart meters, IoT devices, and power generation stations, providing a clear, real-time look at power usage.

Machine learning can use this data to anticipate and prevent massive power outages in the grid. Machine learning helps identify non-obvious patterns in the data that can be a precursor to grid failure, which helps maintenance teams preempt failure.

Balancing the Grid

Balancing the grid — making sure energy supply matches energy demand — is one of the most important jobs a transmission operator has. But renewable energy sources depend heavily on the weather, making them harder to predict.

Transmission operators spend millions each year fixing planning mistakes that lead to producing too much or too little power. In hybrid systems — which rely on both renewable energy sources and fossil fuels to generate electricity — these mistakes have to be corrected at the last minute by buying more energy or compensating power plants for the excess.

Machine learning is the most accurate method available to forecast the output of renewable energy. Advanced methods, like Long Short-Term Neural Networks (LSTMs), can weigh the many factors involved — wind, temperature, sunlight, and humidity forecasts — and make the best predictions. This saves money for operators and preserves resources for power plants.

Preventing Blackouts and Brownouts With Real-time Monitoring and AI Prediction

Power grids have a lot of obstacles to overcome in providing continuous energy to customers. Weather patterns, usage, internal failure, even wildcard incidents like lightning strikes and interference from wild animals can all affect power delivery.

Machine learning is increasingly being used to help predict potential brownout and blackout conditions. By feeding historical data into the AI and running Monte Carlo simulations to predict potential outcomes, grid operators can use machine learning to identify conditions that could lead to grid failure. And they can act accordingly.

Sensors like phase measurement units (PMU) and smart meters can provide usage information in real-time. When combined with both historical and simulation data, AI can help mitigate potential grid failure, using techniques like grid balancing and demand response optimization. Incidents that would otherwise have affected millions of people can be contained to a smaller area and fixed faster for less money.

Differentiate Power System Disturbances from Cyber Attacks

Cyber attacks are increasingly used to target important infrastructure, like shutting down hospitals with Ransomware attacks (when attackers break into the system and lock legitimate users out until a ransom is paid). With utility grids, a cyber attack can have widespread consequences and affect millions of users.

Detecting these attacks is critical.

Developers are using machine learning to differentiate between a fault (a short-circuit, for example) or a disturbance (such as line maintenance) in the grid and an intelligent cyber attack (like a data injection).

Since deception is a huge component of these attacks, the model needs to be trained to look for suspicious activity – things like malicious code or bots – that get left behind after the deception has occurred.

One such method uses feature extraction with Symbolic Dynamic Filtering (an information theory-based pattern recognition tool) to discover causal interactions between the subsystems, without overburdening computer systems. In testing, it accurately detected 99% of cyber attacks, with a true-positive rate of 98% and a false-positive rate of less than 2%. This low false-positive rate is significant because false alarms are one of the biggest concerns in detecting cyber attacks.

Balance Supply and Demand

Utility providers are looking for ways to better predict power usage while maintaining maintaining energy supply at all times. This becomes critical when renewable power sources (like solar or wind) are introduced into the grid.

Because these renewable power sources rely on elements beyond human control (like the weather), utility providers know they can’t always rely on renewables for continuous production. Knowing precisely when demand levels will peak allows utility providers to connect to secondary power sources (like conventionally generated electricity) to bolster the available resources and ensure constant service provision.

More and more utility providers are turning to machine learning for help. We can feed historical data into machine learning algorithms -- like Support Vector Machines (SVM) -- to accurately forecast energy usage and ensure sufficient levels and constant supply.

Detect Power Grid Faults

Current methods for detecting faults in the grid consume a lot of unnecessary time and resources. This creates a situation where power transmission is interrupted and customers are without electricity while faults are first located, then fixed.  

Machine learning can find faults quickly and more accurately helping you minimize service interruption for your customers.. Support Vector Machines (SVM) are combined with Discrete Wavelet Transformation (DWT) to locate faults in the lines using a traveling wave-based location method.

When we apply  DWT (a form of numerical and functional analysis that captures both frequency and location information) to the transient voltage recorded on the transmission line, we can determine the location of the fault by calculating aerial and ground mode voltage wavelets. So far, this method has detected fault inception angles, fault locations, loading levels, and non-linear high-impedance faults for both aerial and underground transmission lines.

Detect Non-Technical Power Grid Losses

In the energy world, “non-technical losses” means energy theft or fraud from the system.

There are two common types of non-technical losses. The first is when a customer uses more energy than the meter reports. The second involves rogue connections stealing energy from paying customers. To pull off this theft or fraud, bad actors can bypass smart meters completely or insert chips into the system that change how meters track energy use. Meter readers can also be bribed to report lower numbers (though thanks to smart meters, this is increasingly hard to do).

Because these non-technical losses cost $96 billion annually, utility providers are turning to machine learning to combat the problem.

We can help utility providers mine historical customer data to discover irregularities that indicate theft or fraud. These can be things like unusual spikes in usage, differences between reported and actual usage, and even evidence of equipment tampering.

Energy Distribution

Better Predict Energy Demand

Accurately predicting customers’ energy needs is critical for any utility provider. To date, we haven’t found an adequate solution for bulk energy storage, which means energy needs to be transmitted and consumed almost as soon as it’s produced.

We're using machine learning to increase the accuracy of these predictions. Historical energy use data, weather forecasts, and the types of businesses or buildings operating on a given day all play a role in determining how much energy is used.

For example, a hot summer day mid-week means more energy usage because office buildings run air conditioning at a high capacity. Weather forecasts and historical data can help identify those patterns in time to prevent rolling blackouts caused by air conditioners in the summer.

Machine Learning finds complicated patterns in the various influencing factors (such as day, time, predicted wind and solar radiation, major sports events, past demand, mean demand, air temperature, moisture and pressure, wind direction, day of the week, etc.) to explain the development of demand. Because machine learning finds more intricate patterns, its predictions are more accurate. This means energy distributors can increase efficiency and decrease costs when they buy energy – without having to make expensive adjustments.

Energy Generation

Predict Turbine Malfunction

Wind is a great renewable energy source, but wind turbine maintenance is notoriously expensive. It accounts for up to 25% of the cost per kWh. And fixing problems after they occur can be even more expensive.

Machine learning can help you get ahead of this problem. The goal is to reduce maintenance costs by catching problems before the turbine malfunctions. This is particularly important when wind farms are located in hard-to-access places, such as the middle of the ocean, which makes repair costs even higher.

Real-time data gathered with Supervisory Control and Data Acquisition (SCADA) can help identify possible malfunctions in the system far enough in advance to prevent failure.

For example, data from sensors found within the turbines – such as oil, grease, and vibration sensors – have been used to train machine learning models to identify precursors to failure, such as low levels of lubricant.

This method can train machine learning models to predict failures up to 60 days in advance.

Consumption / Retail

Accurately Predict Energy Prices

As personal power generation (using solar or wind power) gets easier and cheaper, consumers and businesses are increasingly producing their own power.

Personal power generation allows people to make, consume, and store their own energy. Depending on where they live, they may even be able to sell surplus power back to the local power utility.

Machine learning can help find the best time to produce, store, or sell this energy. Ideally, energy should be consumed or stored when prices are low and sold back to the grid when prices are high.

By looking at historical data, usage trends, and weather forecasts, machine learning models have made accurate predictions on an hourly basis. People with personal and business energy generation systems can use these predictions to make strategic decisions about whether to use, store, or sell their energy.

For example, Adaptive Neural Fuzzy Inference System (ANFIS) has been used to predict short-term wind patterns for wind power generation. This allows producers to maximize energy production and sell it when energy prices are at their peak.

Reduce Customer Churn

In open energy markets, where customers have a choice of utility providers, understanding which customers are going to churn out can be critical. Churn rates, which is the percentage of customers who stop using your service in a year, can be as high as 25%. Being able to predict churn and stay ahead of it is essential to survival.

Machine learning is helping utility owners predict when a customer is getting ready to churn out. By using techniques such as Cross-industry Standard Process for Data Mining (CRISP-DM), AdaBoost, and Support Vector Machines, as well as historical usage data, utility providers can identify key indicators of whether or not a customer is going to churn. These indicators include things like customer satisfaction, employment status, energy consumption, home ownership or rental status. A change in any of these can indicate a customer is getting ready to terminate their service.

When these indicators are identified far enough in advance, it’s possible to avoid churn by working with customers to solve any problems they’re experiencing.

Energy Trading

Predict Energy Prices

Just like natural gas and oil, wholesale energy is a market commodity. So naturally it's important for traders to be aware of market fluctuations and pricing when it comes to buying and selling energy.

To help make sense of the massive amounts of data used to make trading decisions, traders are increasingly turning to machine learning.

A mix of statistical analysis and machine learning can help commodity traders make better predictions. Classical statistical analysis techniques like time series analysis, Seasonal Autoregressive Integrated Moving Average (SARIMA), and regression models are used to deal with the data. And machine learning makes connections between the various data points.

What’s more, machine learning trains itself to make increasingly accurate predictions using the constant flow of real-time data.

Keep reading

No items found.
No blog posts found.