The State of AI and Machine Learning Report is an annual exploration of the strategies implemented by companies large and small, across industries and continents as they advance in their AI maturity. The 8th edition of this report highlights the prevailing approaches to data management and security, responsible AI, and the significant role played by external data providers in advancing progress. As companies are advancing in AI maturity, we see an even bigger focus on ethics and data diversity.

ON-DEMAND

Listen to our leaders as they discuss the hottest trends in AI for 2022

WATCH NOW

Considered a challenging step of the AI lifecycle, data sourcing remains an obstacle

42% of technologists say the data sourcing stage of the AI lifecycle is very challenging. However, business leaders were less likely to report data sourcing as very challenging (24%).

Figure 1:
For each of the following stages, how challenging is it for you/your organization to complete the stage?

Find Each Stage of the Data for the AI Lifecycle Very Challenging

Bar Graph
Radar Graph

Business leaders and technologists report a gap in the ideal vs. reality of data accuracy

More than half of respondents say data accuracy is critical to the success of AI but only 6% reported achieving data accuracy higher than 90%.

Figure 2a:
How critical is the data accuracy for your specific AI use case?
Figure 2b:
What % of accuracy do you typically get in the training data sets you work with?

The gap between data scientists and business leaders is slowly narrowing year over year when it comes to understanding the challenges of AI. The emphasis on how important data, especially high-quality data that match with application scenarios, is to the success of an AI model has brought teams together to solve for these challenges.

Humans are still a very important component in data for the AI lifecycle

There’s a strong consensus around the importance of human-in-the-loop machine learning with 81% stating it's very or extremely important and 97% reporting human-in-the-loop evaluation is important for accurate model performance.

Figure 3:
How Often Are You Updating Your Machine Learning Models?

Machine Learning Model Update Frequency (US-based)

^Only applicable for ‘21/’22

Perceptions regarding the prominence of AI in business may be shifting

Technologists are split on whether their organization is ahead or even with others in their industry. Respondents in the US are more likely than their European counterparts to say their organizations are ahead of others in their industry at adopting AI.

Figure 4:
When it comes to adopting AI, would you say that your organization is:

When It Comes to AI Adoption Your Organization Is:

Total
By Market

Our clients tell us AI is integral to their digital transformation programmes. AI initiatives within the UK and Europe have been established to fast track and improve business processes and help deliver sustainable growth in the tough economic climate of today. They tell us that, though AI strategies are displacing and disrupting elements of traditional business models, the technology is being introduced to bring about business benefits, cost savings, resilience as well as innovation strategies for growth.

Figure 5:
At my organization, responsible AI is a foundation of all AI projects

Responsible AI Is the Foundation of All AI Projects

One of the greatest challenges in our industry is the perception that artificial intelligence poses ethical risks. 93% of respondents agree that responsible AI is a foundation for all AI projects within their organization. As diversity and inclusion become more prominent parts of mainstream AI and ML conversation, ethics at all phases of the AI lifecycle is more important than ever.

Data ethics isn’t just about doing the right thing, it’s about maintaining the trust and safety of everyone along the value chain from contributor to consumer.