Key Performance Indicators (KPIs) are quantifiable and measurable values that reflect your business performance. Tracking KPIs helps you monitor progress towards specific goals and objective and as a business owner you want to maximise every opportunity to increase your profits [1].
By monitoring KPIs you gain insights into business performance, enabling you to improve areas which scored unsatisfactory results in areas such as: competitiveness, profitability or operational efficiency, to name a few [2].
The better the quality of your data, the more valuable your KPIs become, enhancing your evidence-based decision-making. For this reason data must be regarded as a strategic asset by all in the organisation [3] .
Not surprisingly, you want to measure the right things – such aspects of your business which are directly linked to its survival and prosperity. This highlights the importance of aligning your KPIs with your business strategy and the strategic objectives.
Moreover the definition of a KPI and its ultimate objective is of key importance. Imagine a situation where the number of patents in your organisation is expected to indicate the business’ innovativeness. In reality this KPI may encourage your team to go for quantity (large number of “worthless” patents stretching your budget) rather than quality (patents boosting your business’ value: market share, company valuation, revenue, etc.). When creating KPIs consider defining:
In summary, here are some characteristics of ineffective KPIs:
Even the best intentions can lead to the creation of KPIs that drive unintended, negative consequences and behaviours.
Consider the following KPIs’ scenarios and evaluate their likely short- and long-term consequences on business performance:
The importance of imagining or foreseeing relationship, both pros and cons, between KPIs and intended objectives cannot be overstated.
Traditionally, executives have designed and defined KPIs based on their life-long experience and past market trends. This might have worked in times of stability, however today in an era marked with of uncertainty (growing inflation, rising energy prices¸ higher loan cost and fluctuating interest rates), KPIs defined in traditional way increasingly fail to deliver the insights leaders need to succeed today. Traditional KPIs fall short in tracking progress, aligning people and processes, prioritising resources, and advancing accountability.
A BCG’s survey reveals that 60% of managers believe that they need to improve their KPIs, with one-third (34%) already using AI to create new KPIs. Nine out of ten managers within that 34% agree or strongly agree that their KPIs have been improved by AI [4].
Can AI make any difference?
Smart KPIs powered by Artificial Intelligence (AI) have the potential to become a great support, differentiator, challenging and improving business assumptions around performance, profitability, and growth.
Organisations that invest in algorithmic innovations to make their performance metrics more adaptive and predictive expect KPIs to become a source of strategic differentiation and value creation. Intelligent algorithms based on large data models are much better at “tracking” or imagining future trends, fresh perspectives and previously unimagined metrics.
These AI-powered KPIs are also expected to prevent undesirable outcomes, that may result from a failure to regularly re-examine assumptions underlying legacy KPIs.
Increasingly, companies are embedding governance processes and functions that oversee KPIs development and ensure detailed, accurate, and relevant performance data. The objective – a KPI’s quality is explicitly considered during its design and not as a coincidental afterthought [4].
Since “what gets measured gets managed”, better data drive unique opportunities for strategic differentiation and value creation.
The third quarter of 2022 marked the moment when one branch of AI the Gen AI exploded into the public consciousness and by 2023, it began to take root in the business world. АI, however, is a concept that has been with us since the 1950s.
AI exhibits the ability to learn on its own and integrate its existing knowledge to develop innovative and unconventional solutions without human involvement or intervention. It is worth noting that we don’t fully understand this process and, consequently, won’t be able to control it.
Machine Learning (ML) is a subset of AI that uses statistical learning algorithms to build systems capable of automatically learning and improving from experience without being programmed, whilst deep learning (a technique within ML technique) is inspired by how human brain filters information
Since the focus in this article is on Generative AI (also called Gen AI) it is worth mentioning that this form of AI is dominating recent discussions due to its perceived impact on increasing productivity for businesses and individuals. Such perception has been exemplified by tools such as ChatGPT, Gemini or LLaMa.
How does it work? Gen AI relies on large language models (LLM) that access vast amounts of data. When you make a request (a prompt), the AI identified patterns and relationships in the datasets to provide a response. This may include fresh, although not necessarily new in my opinion, content such as text, image, video, audio, or software code [5].
In 2024, organisations and industries began rethinking their business processes and the value of human resources, pushing GenAI to the peak of what seems to be an overinflated expectation due to media hype and marketing. AI is yet to demonstrate advantages over human capabilities for complex decision making and problem-solving.
For now be mindful of some challenges with Gen AI:
Despite these challenges, AI’s phenomenal and unquestionable advantage is data analytics (especially large datasets) and insights generation. Organisations that create new KPIs using AI are more likely to see more efficiency, stronger alignment, increased collaboration and more accurate forecasts than organisations that do not create new KPIs using AI [4]. Why? Because AI with an access to large datasets has the ability to anticipate market conditions, supply chains, and consumer behaviour with greater precision.
Here are a few examples of businesses using AI to generate their KPIs:
Example 1: Pernod Ricard, $10 Billion Global Spirits Business with strong history of mergers and acquisitions, distributing approximately 240 liquor brands in more than 70 countries
This company uses AI to deepen the connection between their profit margins and market share, which in the past were handled in silos – the first one by their finance and the second by the sales function. Today, instead of seeking to maximize each individual KPI, the spirits maker seeks to optimise both KPIs in concert. For instance, they analyse how profit improving commercial and marketing investments (e.g. media or in-store activation) influence market-share objectives. AI helps them better align market share KPIs, margin KPIs and required investment to reach both of them. In an interview with BCG Pierre-Yves Calloc’h, Pernod Ricard’s chief digital officer said: “If you can imagine moving a cursor between market share optimisation objectives and margin optimisation objectives, you need to know how the required investments vary to reach these objectives”.
Given the sheer number of brands under Pernod Ricard’s umbrella, Calloc’h explains how measuring marketing impact at appropriate scales has long been a challenge for the company. This capability transformed how Pernod Ricard’s leadership allocates capital and balances its aspirations for profitability and market share [4].
Example 2: Schneider Electric, $34.2B French based Energy Distribution Company
This company models dynamic KPIs that:
Such dynamic KPIs invite businesses to anticipate changing and unpredictable environments and markets earlier and respond to them more effectively.
Whilst their Chief Governance Officer, Hervé Coureil, acknowledges that harnessing data can be costly and time-consuming, he contends this to be strategically necessary. “We want our KPIs to evolve over time because we don’t want to drive our business on legacy or vanity metrics,” he says. To ensure that KPIs develop in accord with changing objectives and new measurement capabilities, Coureil cosponsored a performance management office (PMO) to oversee performance standards. “We looked at performance measurement as one of our transformation drivers,” he says. The PMO helped top management evolve its portfolio of KPIs and align them with the company’s various operating units. It also pushed the businesses to become more data driven and analytically aware of the links between performance improvements, improved metrics, and enhanced outcomes [7].
Example 3: Singapore’s based DSB Bank
The bank leadership created cross-functional groups to improve its customer focus, customer service, and profitability. Departing from a traditional operational approach, where each department owned separate KPIs for its distinct customer touch points, they took three years to create a value map. That map enabled them to manage a “customer journey” that comprises outcomes in four categories: customer experience, employee experience, profitability, and risk. AI offered them fresh perspectives on visible and hidden performance patterns and identified key interdependencies among the performance drivers. According to Sameer Gupta, the group’s Chief Analytics Officer and Managing Director at DBS Bank, identifying interdependencies among drivers and KPIs was a fundamental shift that enabled all group members to see the same data, continually assess the factors driving different outcomes, and agilely respond [4].
To make AI effective in your efforts to improve performance measurement, you need these in place:
Here are examples of ChatGPT-4o and Gemini prompted to imagine a brainstorming session where functional business leaders were invited to reimagine smart KPIs. Neither the prompts nor the responses have been modified.
Take a look how these suggestions demonstrate the potential of Gen AI to generate innovative and impactful KPIs that align with business goals and improve overall performance. As generative AI continues to evolve, trained on new data, its influence on KPI design and development is bound to grow stronger.
Have you used AI to create your business’s performance metrics and seen the value? Please feel free to share your experience.
ChatGPT-4o Response 1
To propose high-impact Key Performance Indicators (KPIs) for Customer Lifetime Value (CLV) and customer relationship management, it’s crucial to gather comprehensive inputs and guide the brainstorming session with well-defined prompts. While I can’t access real-time data directly, I can suggest a structured approach and key inputs that you can gather and analyze to develop these KPIs. Here’s a detailed plan:
Inputs Required for High-Impact KPIs:
Prompts for Brainstorming Session:
Real-Time Data Support:
While I can’t directly access real-time data, I recommend setting up a robust data infrastructure that includes:
These systems will provide the necessary data to develop, refine, and track high-impact KPIs for CLV and overall customer relationship management.
ChatGPT-4o Response 2
With access to comprehensive data and information, here are some innovative KPIs that can be brainstormed to measure the potential future value of customers:
These KPIs are designed to go beyond traditional metrics, incorporating predictive analytics, behavioral data, and qualitative insights to provide a comprehensive view of the potential future value of customers. They can help identify high-potential customers, enhance personalized marketing strategies, and optimize customer lifetime value.
Gemini – Response 1
To effectively guide the brainstorming session and propose high-impact KPIs for customer lifetime value (CLTV), I would need the following inputs:
To encourage innovative thinking and uncover novel KPIs, I would use the following prompts:
Access to real-time data would be invaluable for this brainstorming session. It would allow us to:
Note: The specific data sources and level of real-time access will depend on the company’s IT infrastructure and data management capabilities.
By combining these inputs, prompts, and data access, we can create a dynamic and productive brainstorming session that generates high-impact KPIs for measuring customer lifetime value.
Would you like to explore specific examples of potential KPIs based on a hypothetical business model?
Gemini – Response 2
Innovative KPIs to Measure Future Customer Value
Imagine you run a cool online gaming company. Let’s brainstorm some super-cool ways to measure how awesome your players will be for your business in the future.
Looking Ahead: Future-Focused KPIs
Beyond the Game: Real-World Impact KPIs
Remember, these are just ideas to get your imagination going. The best KPIs are the ones that help you understand your players better and make your games even more awesome!
Would you like to brainstorm some KPIs for a different kind of business?
Copyright© 2020-2024 Simplarity Limited
