Share on facebook
Share on linkedin
Share on twitter
Share on facebook
Share on linkedin
Share on twitter

Dealing With 5 Practical Issues in Machine Learning and Their Business Implications

Author | Dr. Shou-De Lin, Chief Machine Learning Scientist, Appier

Businesses today deal with more data and it’s arriving faster than ever before. At the same time, the competitive landscape is changing rapidly so the ability to make fast decisions is critical.

As Jason Jennings and Laurence Haughton put it “It’s not the big that eat the small… It’s the fast that eat the slow”.

Business success comes from making fast decisions using the best possible information.

Machine learning (ML) is powering that evolution. Whether a business is trying to make recommendations to customers, hone their manufacturing processes or anticipate changes to a market, ML can assist by processing large volumes of data to better support companies as they seek a competitive advantage.

However, while machine learning offers great opportunities, there are some challenges. ML systems rely on lots of data and the ability to execute complex computations. External factors, such as shifting customer expectations or unexpected market fluctuations, mean ML models need to be monitored and maintained.

In addition, there are a number of practical issues in machine learning to be solved. Here we will take a close look at five of the key practical issues and their business implications.

 

1. Data Quality

Machine learning systems rely on data. That data can be broadly classified into two groups: features and labels.

Features are the inputs to the ML model. For example, this could be data from sensors, customer questionnaires, website cookies or historical information.

The quality of these features can be variable. For example, customers may not fill questionnaires correctly or omit responses. Sensors can malfunction and deliver erroneous data, and website cookies may give incomplete information about a user’s precise actions on a website. The quality of datasets is important so that models can be correctly trained.

Data can also be noisy, filled with unwanted information that can mislead a machine learning model to make incorrect predictions.

The outputs of a ML model are labels. The sparsity of labels, where we know the inputs to a system but are unsure of what outputs have occurred, is also an issue. In such cases, it can be extremely challenging to detect the relationships between features and the labels of a model. In many cases, this can be labor intensive as it requires human intervention to associate labels to inputs.

Without accurate mapping of inputs to outputs, the model might not be able to learn the correct relationship between the inputs and outputs.

Machine learning relies on the relationships between input and output data in order to create generalizations that can be used to make predictions and provide recommendations for future actions. When the input data is noisy, incomplete or erroneous, it can be extremely difficult to understand why a particular output, or label, occurred.

 

2. The Complexity and Quality Trade-Off

Building robust machine learning models requires substantial computational resources to process the features and labels. Coding a complex model requires significant effort from data scientists and software engineers. Complex models can require substantial computing power to execute and can take longer to derive a usable result.

This represents a trade-off for businesses. They can choose a faster response but a potentially less accurate outcome. Or they can accept a slower response but receive a more accurate result from the model. But these compromises aren’t all bad news. The decision of whether to go for a higher cost and more accurate model over a faster response comes down to the use case.

For example, making recommendations to shoppers on a retail shopping site requires real-time responses, but can accept some unpredictability in the result. On the other hand, a stock trading system requires a more robust result. So, a model that uses more data and performs more computations is likely to deliver a better outcome when a real-time result is not needed.

As Machine Learning as a Service (MLaaS) offerings enter the market, the complexity and quality trade-off will come to greater attention. Researchers from the University of Chicago looked at the effectiveness of MLaaS and found that “they can achieve results comparable to standalone classifiers if they have sufficient insight into key decisions like classifiers and feature selection”.

 

3. Sampling Bias in Data 

Many companies use machine learning algorithms to assist them in recruitment. For example, Amazon discovered that the algorithm they used to assist with selecting candidates to work in the business was biased. And researchers from Princeton found that European names were favored by other systems, mimicking some human biases.

The problem here isn’t the model specifically. The problem is that the data used to train the model comes with its own biases. However, when we know the data is biased, there are ways to debias or to reduce the weighting given to that data.

The first challenge is in determining if there is inherent bias in the data. That means conducting some pre-processing. And while it may not be possible to remove all bias from the data, its impact can be minimized by injecting human knowledge. 

In some cases, it may also be necessary to limit the number of features in the data. For example, omitting traits such as race or skin color can help limit the impact of biased data on the results from a model.

 

4. Changing Expectations and Concept Drift

Machine learning models operate within specific contexts. For example, ML models that power recommendation engines for retailers operate at a specific time when customers are looking at certain products. However, customer needs change over time, and that means the ML model can drift away from what it’s designed to deliver.

Models can decay for a number of reasons. Drift can occur when new data is introduced to the model. This is called data drift. Or it can occur when our interpretation of the data changes. This is concept drift.

In order to accommodate this drift, you need a model that continuously updates and improves itself using data that comes in. That means you need to keep checking the model.

That requires the collection of features and labels and to react to changes so the model can be updated and retrained. While some aspects of the retraining can be conducted automatically, some human intervention is needed. It’s critical to recognize that the deployment of a machine learning tool is not a one-off activity.

Machine learning tools require regular review and update in order to remain relevant and continue to deliver value.

 

5. Monitoring and Maintenance

Creating a model is easy. Building a model can be automatic. However, maintaining and updating the models requires a plan and resources.

Machine learning models are part of a longer pipeline that starts with the features that are used to train the model. Then there is the model itself, which is a piece of software that can require modification and updates. That model requires labels so that the results of an input can be recognized and used by the model. And there may be a disconnect between the model and the final signal in a system.

In many cases when an unexpected outcome is delivered, it’s not the machine learning that has broken down but some other part of the chain. For example, a recommendation engine may have offered a product to a customer, but sometimes the connection between the sales system and the recommendation could be broken, and it takes time to find the bug. In this case, it would be hard to tell the model if the recommendation was successful. Troubleshooting issues like this can be quite labor intensive.

 

Machine learning offers significant benefits to businesses. The ability to predict future outcomes in order to anticipate and influence customer behavior and to support business operations are substantial. However, ML introduces a number of challenges to businesses. By recognizing these challenges and developing strategies to address them, companies can ensure they are prepared and equipped to handle them.

 

* Want to know more about how you can leverage machine learning to elevate your business and improve your marketing effectiveness? We are here to help! Get in touch with our team today for an exclusive consultation.

WE ARE HERE TO HELP

Let us know the marketing challenges that you’re facing, and how you want to improve your marketing strategy.

YOU MIGHT ALSO LIKE

Maximize App Engagement With Push Notifications (Industry Examples Included)

Having high app downloads is not much good if your customers don’t use your app. Thankfully, you can increase your app engagement and help your brand play a bigger part in your customers’ lives through the judicious use of app push notifications.    The State of App Engagement There has been an explosion in demands for mobile apps in recent years, and global consumer spending reached US$120 billion on apps — a figure that is up 2.1x from 2016.  Consumers love apps, as do brands. It is a great way to meet your customers’ needs and because they are on mobile devices, your customers can engage with your brand wherever they are. However, to give your customers a reason to stick with your app, you need to craft your app engagement strategy carefully, and push notifications can be a great way to remind them about your app and what you have to offer.   Why Use Personalized Push Notifications? As a marketer, push notifications can be your greatest asset or your worst enemy. Using them correctly offers you a fantastic way to engage your users with personalized, timely promotions that increase their level of engagement with your brand. However, misuse

Ask the Experts: General Assembly’s Aziza Sheerin on Upskilling for Digital Transformation

Aziza Sheerin, Regional Director for General Assembly, recently spoke to us about technology skills required for driving digital transformation, and how people can apply those in their organizations.   Can you tell us a bit about your role at General Assembly and what GA does? General Assembly started out in 2011 in New York City, and we’ve now scaled to more than 32 cities across 4 continents. GA enables individuals and enterprises to acquire today’s most in-demand skills in areas such as data science, digital marketing, software engineering, user experience design, and product management. We want to make the future work for everyone. I joined GA five years ago as the first person on the ground in Singapore. I’m responsible for growth, strategic partnerships, and operations in this region.   Many people want to gain technical skills to stay relevant to their employers, and employers want to accelerate digital transformation by having more people with technology skills. There’s discussion and evidence that businesses are accelerating digital transformation due to the pandemic. Are you seeing this reflected in requests from both individuals and organizations? We’ve seen interesting shifts happen during this period as a result of the pandemic, both by employers

How Emotional AI Can Benefit Businesses

Author | Min Sun, Chief AI Scientist, Appier Emotion is one of the most distinguishable human qualities, one that sets us apart from machines. However, it is not out of the realm of possibilities for machines to read emotions and respond accordingly. Increasingly, machines are able to interpret human’s emotional states and adapt their behavior to give appropriate responses – something we call emotional AI, or artificial emotional intelligence (though in the computing field, it is known as affective computing). Here we will explore what it is, how it works, and how it can benefit businesses.   Three Types of Emotional AI Emotional AI is the next step in the evolution of artificial intelligence. By interpreting people’s emotions, AI can respond in a much more naturalistic manner, making the interaction much closer to typical human intercourse.   There are three main types of emotional AI – natural language text analysis, voice analysis and facial expression analysis. The first two are already quite common, while the third probably attracts the most media attention. Other types of analysis also include mouse movement, eye-gaze, heart rate and electrocardiography, etc. Natural language text analysis It involves AI scanning written text like a review of a