Artificial Intelligence (AI) can analyse large datasets, automate mundane tasks, and improve business decision-making processes. AI-powered demand forecasting and planning can be used to streamline the buying process, manage in-season markdowns more effectively, and provide accurate demand forecasts – all of which ultimately translate into stronger margins. 

We need to look at the data science behind AI and answer the question "how does it work." By understanding how AI works and using what we can leverage from the emerging data science, we can develop both confidence and discernment when utilising AI.

"Know Before You Go"— How Can AI Work for You?

To understand AI or machine learning (ML), first consider that it's not a "one-size-fits-all" tool. There are several types of AI models, including supervised learning, unsupervised learning, and reinforcement learning. These models enable AI systems to recognise patterns, classify information, and make decisions based on data inputs. 

There are webpages listing what are said to be among the more popular AI models—the algorithms and mathematical representations that allow machines to learn from data and make predictions or decisions. Selecting the right model means data scientists can create powerful AI systems for automation and insights that would prove impossible or at least extremely complex and time-consuming for people to achieve.

To select the right model, there are several key topics to understand:

1. Data collection and preprocessing: Before we can build AI models, we need to gather relevant data and clean it. This may involve handling missing values, dealing with outliers, and normalising data to ensure that the input features are on a similar scale.
2. Exploratory data analysis (EDA): This is the process of visualising and summarising the data to gain insights, identify patterns, and formulate hypotheses for further analysis. EDA helps us understand the underlying structure of the data and informs the selection of appropriate machine learning algorithms.
3. Feature engineering: This involves the process of selecting and transforming the most relevant variables, or "features," from the raw data to improve model performance. Feature engineering may include techniques such as dimensionality reduction, feature scaling, and feature extraction.
4. Machine learning algorithms: These are the core of AI systems and can be divided into three main categories – supervised learning, unsupervised learning, and reinforcement learning. Some popular algorithms include linear regression, decision trees, support vector machines, clustering algorithms, and neural networks.
5. Model selection and evaluation: Choosing the right model and evaluating its performance is crucial. This involves splitting the data into training and testing sets, selecting the best model based on performance metrics (e.g., accuracy, precision, recall), and fine-tuning the model to achieve optimal results.
6. Model deployment: Once a suitable model has been developed, it must be deployed for real-world use. This may involve integrating the model into existing systems, monitoring its performance, and updating it as new data becomes available.
7. Ethical considerations: AI systems have the potential to impact society in significant ways. It is important for data scientists to consider the ethical implications of their work, such as fairness, transparency, and privacy.

However, if consumer packaged goods companies (CPGs) and retailers don't ask the right business questions or have inaccurate data, they can use AI incorrectly—and it won't work the way they intended. Here are some hypothetical examples for CPG and retail concerns:

CPGs:

1. Incorrect data inputs: A CPG company may try to use AI to predict consumer demand for every location and SKU, but if the data inputs are incorrect or incomplete, the predictions may be inaccurate. For example, if the company doesn't consider local events or promotions that may affect demand, the AI system may not be able to accurately predict demand in that location.
2. Overreliance on legacy solutions: CPG companies may be using legacy solutions that aren't able to keep up with the demands of modern business. If they rely too heavily on these solutions, they may miss out on the benefits of AI. For example, if a company is using a legacy demand forecasting solution that can't handle large datasets or provide real-time updates, they may miss out on opportunities to improve their margins.
3. Lack of understanding of AI: CPG companies may not fully understand how AI works or how to use it effectively. For example, they may not understand the importance of data quality or how to select the right AI model for a particular task.

Retailers:

1. Failure to ask the right business questions: Retailers may fail to ask the right business questions, leading to inaccurate or irrelevant data inputs. For example, if a retailer is trying to predict omnichannel demand for all products across channels and time frames, but they don't consider changing market conditions or customer preferences, the predictions may not be useful.
2. Inaccurate data inputs: Retailers may also face challenges with inaccurate data inputs. For example, if a retailer is trying to ensure that they have the right product, at the right place, time, and price, but they're relying on inaccurate or incomplete data, they may miss opportunities to improve their margins.
3. Lack of integration with legacy systems: Retailers may also struggle to integrate AI with their legacy systems. For example, if a retailer is using an outdated inventory management system, they may not be able to take advantage of the benefits of AI-powered demand forecasting or pricing optimisation.
   

To avoid these pitfalls, it's important for companies to approach AI strategically and with a clear understanding of their business needs. They should take steps to ensure that their data inputs are accurate, that they're using the right AI models for their specific tasks, and that they're integrating AI effectively with their legacy systems.

You can read more about AI-powered demand forecasting here or reach out to Nicholas and Alex directly.