Traditional analytics have served the data-driven retail industry admirably for decades. However, Artificial Intelligence and Machine Learning have introduced a completely new level of data processing that leads to more in-depth business insights.
We’ve grown accustomed to hearing about advancements in the field of machine learning implementation through the lens of self-driving automobiles and talking robots. But what if we examine how machine learning affects more familiar industries, such as retail?
According to CB Insights, 374 Artificial Intelligence start-ups raised $1.8 billion in 374 deals between 2013 and 2018. Amazon can claim credit for these impressive figures because they persuaded business leaders to reconsider the use of Artificial Intelligence in retail – both physical stores and e-commerce strategies – in order to stay ahead of the competition.
Why does retail need machine learning?
Retailers’ survival is based on their ability to predict. Using AI and automated machine learning tools, you can save money and time by predicting how many goods will be required on a given day. Machine learning and artificial intelligence (AI) can also be very useful in optimising purchases, inventory, and sales.
According to Juniper Research, retailers’ annual spending on artificial intelligence will increase by 230% – from $3.6 billion in 2020 to $12 billion in 2023. The use of machine learning tools for demand forecasting will be the primary focus of machine learning implementation in retail.
To sum it up, what can machine learning offer to retailers?
Retailers should consider various aspects of individual department management in geographically dispersed areas to ensure a consistent supply flow with lower costs and minimised losses. The machine learning platform is confronted with the following challenges:
- Customer interaction analysis using virtual assistants and chatbots;
- Inventory and supply chain management with assortment planning;
- Execution of retail analytics on a scale to understand annual growth;
- Personal recommendations utilising collaborative filtration, content filtration, hybrid filtering, etc;
- Interpretation of text and images from invoices, packing lists, bills, etc.
- Detection of item shortfalls in stores;
Examples of machine learning in retail.
In 2018, the Swedish H&M division began using machine learning to select a range of stores. This way, the company hoped to entice retail chain customers to compensate for the worst sales in its history: H&M’s sales have fallen for 10 consecutive quarters in its 71-year history.
Analysts are sceptical of H&M’s business strategy. However, one H&M store in a wealthy district of Stockholm demonstrates that machine learning can be extremely beneficial. Because the managers were oriented toward local residents, this store focused on products for the entire family.
However, the analysis showed that the majority of customers were women and fashionable goods, like flower skirts, sold surprisingly well along with expensive goods. H&M reviewed the store’s assortment and sales grew, although so far, the company refused to disclose how much. The algorithms operate 24/7 and are adjusted to continuously shifting client preferences and expectations.
Machine learning is used to maintain the productivity and sustainability of Costco’s fresh food department. Costco donated all of its unsold or damaged products, and therefore produced more than needed fresh food.
They collaborated with SAP to address this issue by developing a demand forecasting algorithm that assists managers in ensuring that the appropriate quantity of fresh products is always in stock. Costco bakery managers must be able to forecast demand for each menu item that must be produced on a daily basis. Prior to the SAP solution, these managers had to establish a production plan on paper by reviewing sales and trend reports. They also had to review local events and the past background of their colleagues. The plans were updated daily on the basis of previous day’s leftovers, damaged or destroyed products, before the baking teams could start their work in the morning-time. The development of this solution was led by SAP AppHaus, a branch of SAP solutions.
SAP was able to create a new “bakery of the future” with Costco employees after gathering enough information about the bakery manager’s daily tasks. It is a tablet app that displays data and ideas to bakery managers while also automating manual processes. Machine learning is used in the application to provide a planning forecast for each item on the bakery menu. This forecast determines how much of each item is to be baked and is automatically adjusted for the passing residue and damaged items.
In early 2018, the world’s e-commerce giant Amazon opened its first staff-less store Amazon Go for public use. It is not surprising that Amazon decided to try out the latest AI developments not only on the automated payment system.
Amazon Go’s sales departments are all outfitted with high-tech cameras equipped with automatic object identification RFID (Radio Frequency Identification). Typically, such a system is used in unmanned electric vehicles to track the behaviour of passengers in the cabin as well as to automate the processing of visual data by a computer. Amazon Go cameras, on the other hand, went a step further and were used to monitor retail customers’ behaviour from the moment they entered the store until they paid for their purchases. It may sound a little creepy, but it is effective nonetheless.
The cameras are also connected to the store’s automated warehouse system and shelves equipped with ‘Sensor fusion’ sensors. If the customer’s goods cannot be detected, the camera locates them in the warehouse system and coordinates with the weight and movement sensors located on each shelf.
Let’s say the buyer took the milk carton and began to read the composition of the product, but suddenly saw a familiar brand nearby and returned the package to its place. Even during the few seconds it takes to make a decision in Amazon Go, the camera, sensor, and inventory system will be tracking it, and machine learning algorithms will draw the appropriate conclusions.
What next for machine learning in retail?
According to an IBM survey, by 2021, more than 70% of retail and consumer products companies will be using smart automation tools along their supply chains. Here are some fields where retailers intend to utilise AI:
- Supply Chain Planning (85%)
- Demand forecasting (85%)
- Customer Intelligence (79%)
- Marketing and advertising (75%)
- Warehouse operations (73%)
- Pricing and promotion (73%)
Perhaps it is past time to learn how to use machine learning in order to avoid missing the moment when this technology will serve as the foundation for explosive growth. Despite the fact that it has already occurred, hurry up!