Slovenian premium liquid cooling products manufacturer meets customer demand faster with AI
Slovenian company EK Water Blocks is a leading manufacturer of water cooling, extreme cooling, and air-cooling products for computer processors and memory devices—serving customers in more than 30 countries. However, its continued growth quickly made answering to its customer queries a challenge, and EK saw the need to optimize and automate its customer support process. With the help of Microsoft partner CREApro, EK adopted an AI solution using Azure Machine Learning. This has resulted in faster customer service and an increase of customer satisfaction by 10 points. . Slovenian company EK has grown from a small premium liquid cooling product manufacturer to a renowned supplier in the industry. Its customer base now covers individuals and enterprises in 30 countries. While its small team amplifies its success, EK needed the help of technology to support its continued growth. According to Matjaž Krč, CEO at EK, “We want to offer more value to our customers and, at the same time, help our employees be more efficient.” The right customer query in the right place “Customers often have questions regarding our products, so we needed to quickly analyze each query’s nature and urgency to assign them to the most suitable agent, while considering the team’s workload. We also have a customer support team based in the United States, but the classification of those requests was also done manually by the team based in Slovenia, delaying our response to customers there because of the time difference,” explains Robert Osojnik, IT Manager at EK. “So, we decided to automate the process using AI and machine learning.” EK worked with local Microsoft partner CREApro to build its solution on Azure Machine Learning. “With Azure, we could build the infrastructure fast without extra cost or investment on hardware licenses. That also means a fast implementation,” Osojnik adds. Quality service in less time “In three months, we’ve shortened our customer support response time by 30 percent, with the request ticket directly being classified and assigned to the right agent 9 times out of 10. And more importantly, customer satisfaction has increased by 10 points,” Osojnik points out. This solution not only completely removed the time difference issue for the support team based in the United States―who get assigned a request ticket no matter when it was sent by the customer―it also made the Slovenian team’s lives easier. “Before the optimization, one employee had to start working at 6:00 AM to do all the manual ticket classifications. Now, everybody can be in at 8:00 AM,” says Osojnik. “This has made employees very happy, as they can be much more focused on their work with less stress,” he adds. “I see the enormous potential of AI, so we want our other departments to use it as well,” Krč concludes. “For example, we’re currently looking into using AI to optimize inventory and material purchasing, to support our R&D department with product engineering and design, and to help our HR team in their search for new talent.” We’ve shortened our customer support response time by 30 percent. … And more importantly, customer satisfaction has increased by 10 points. Robert Osojnik: IT Manager EK Water Blocks
Using advanced AI for predicting successful sales of shirt designs in textile industry
Textile industry in Slovenia The textile industry in Slovenia and wider region was one of the main industry branches which employed thousands of workers. The roots of this successful development are in industrial revolution of the late 19th century, when new factories started to spring up in many cities in Slovenia which was at the time part of old Austro-Hungarian Empire. After the second world war the new regime started investing even more heavily into the textile industry and Slovenia had one of the most booming growths for several decades. The problem was, with the passing of time, the factories, the machines and working processes were getting more and more obsolete. Modernisation was not the priority and the lack of modern technologies was covered with additional workforce. This all worked fine in the block-divided world before the fall od the Berlin Wall. Yugoslavia was a socialistic country with 5-year plan-based economy. The market was closed, protectionistic and suited for low added value textiles produced in factories all around the country. Of course everything came crashing down after tumultuous events of the early 90’s. Independence, the collapse of Yugoslavia and it’s common market has hit the Slovenian textile industry hard. One of the strongest economic branches in former country was completely unprepared for the changing realities. Many big and important factories folded leaving many workers unemployed and textile schools empty. Becoming the member of EU coupled with globalisation made things even worse for textile industry and right now there have remained only a fistful of textile factories in Slovenia. Tekstina – a success story with a new business model One of those is a factory called Tekstina. It’s located in a small town called Ajdovščina in the western part od our country. The factory itself has a long and proud history. It was established way back in 1828 and has been growing and expanding it’s business ever since. It weathered the great depression, both world wars, nationalisation and denationalization and it’s still doing great, producing textiles for mainly men’s shirts. But of course, producing just these textiles wouldn’t be enough since production in developing countries is far cheaper. The one thing which elevates Tekstina above all is the creation of their own shirt designs. The Tekstina designed shirt textiles are sold all over the world. All the important textile trademarks are the clients of Tekstina factory and many also print their own designs at Tekstina. The quality and being in front of the competition is the creed of the Tekstina factory. In order to stay on the top, the management of Tekstina is trying to employ new technologies and advanced approaches to design and production. Introducing the machine learning and artificial intelligence was a very vital step into optimization of the current business process. Understanting the business Usually, when starting with any kind of machine learning project, we try to learn as much about the business and employed processes as possible. The Tekstina project was no exception. First we’ve looked into the design project since one of the requirements for the latter part of the project was also the autonomous shirt pattern design. The Tekstina designers use a number of mood boards in order for a proper inspiration. Mood board can consist of different pictures, materials, motives and usually follow a trend which defines each collection. The mood board and later inspirational boards are really a very effective initial tool for start with the creative process. The designer will first create the primary design in a special application. After that, several colour variants are produced, so each design has a few variations – it’s interesting for example that brown colour is never a good sell in Australia, but it’s a good bet in Germany. If needed, the shirt pattern is then tiled, so we can get a correct shirt pattern representation. After the pattern is then chosen in the selection process for the collection, the final catalogue is created and is handed to the sales representatives. The business problem As in every textile business, Tekstina designers create two collections per year – Spring/Summer and Autumn/Winter Collection. The design department will create more than 400 design proposals for each collection. Out of those 400, only 150 are then selected for further manufacturing and international sales. The process of selecting these 150 shirt patterns is totally subjective – the management, sales personnel and fashion experts take a look at all proposals and then vote for their selection of proposals. The best rated designs are then chosen for the collection. Of course, there are many hits and also many misses. Since Tekstina produces mostly textiles for men, most of sold designs are in blue colour – these are the designs which do not really need machine learning for helping with the decision making – the goal would be to decrease the number of misses. In view of this problem, we were asked three questions at our initial meeting: Can AI help us with the selection process? Can we predict the sales of the patterns? Can we use the AI for creating new patters? The Data Every machine learning model, regardless how “intelligent” it is, will need one and the most basic thing – quality data which will ensure that we get good and usable results in our working process. And the Tekstina data was a huge challenge indeed! Well, at least part of it … There were two major groups of data – the financial data from the past which is stored in the ERP and is not really problematic itself, AND the images of designs. Now those images are actually the heart of our project and at the beginning, the were A MESS!!! First we had to map every image with the financial data in the ERP. Now, Tekstina has a very unique convention for naming those designs, but we discovered huge inconsistencies in the file system and there was no way for us to automatically pair the designs with the
Smart Pricing: Fine-tuning price strategies
The term Smart Pricing is often associated with offering lodging and tourism experiences. It is used to recommend prices according to accommodation characteristics and automatically adjust them to daily, weekly and seasonal fluctuations in demand. The user can still set the minimum and / or maximum prices he is willing to offer, and include additional hosting restrictions. This price elasticity approach can also be adopted by other businesses and financial scenarios, from banking to insurances. In fact, any service or product price can be estimated using data on market conditions if data is available. What Smart Pricing actually does? It is used to calculate and adjust prices to assure the maximum success probability (individually or quantitatively) and maximize profit. What is required to use Smart Pricing? A precise definition of service or product offered on the market, the limitations that apply when calculating the price and as many of the main influencing factors as possible. Abundant historical offer data, both successful and unsuccessful, that assure a strong and successful model. How does Smart Pricing work? Algorithm can be split into 3 components. Elasticity: This is a probability function estimating the probability that the customer is going to accept the offer. It is calculated using historical data with a suitable method. Profit evaluation: Formula for profit calculation given offer price and costs. Limitations: Minimum or maximum price, regulations, manual market adjustmens, … A machine learning method than connects these components into a holistic and useful model. Example – Bank Loans Each bank has internal and external regulations that must be respected when preparing a personalized offer. Apart from that, the deal has several parameters that are determined during negotiations. Client asks for a specific amount and the bank offers a payment plan and interest rate. The client either accepts or rejects the offer, the latter meaning that the bank must re-prepare the offer. In theory, the bank could offer the most profitable plan at the start and then make tiny steps towards more affordable plan until the client accepts. Unfortunatelly, the client would be fed up with negotiations after a couple of tries and each offer would consume a bank employee for a couple of work hours. Smart Pricing is exactly the approach to solve such dilemmas and to find the optimal offer. Simultaneous optimization on multiple factors is also possible. For example, not optimizing only the interest rate, rather optimizing interest rate and initial depozit at the same time. A similar approach can be used by insurance company, real estate agencies, airlines, energy market, etc.
A brief insight into AI supported customer ticketing
Our company made a special AI interface for sorting and classifying customer support requests. Every client creates a ticket in case of a question or a request for help. The ticket can be created on our customer’s website or emailed. Even though, there are two distinct options available (logistics question or technical support question) and of course, the third, “general” option. In the past, the customer support department spent a lot of time sorting the wrongly submitted requests by hand and it took a lot of working hours to just properly classify them. Since the client’s satisfaction is the primary drive of our customer’s business, the response time and quick resolution of customer issues are vital. The AI solution analyzes every customer request and classifies it. The classification is conducted directly in the customer support tool (via Zendesk platform). During the development of our AI solution, we’ve encountered several challenges: We had to prepare the proper training and test sets from the existing tickets We had to properly verify the results The model had to be the integrated into the existing working process Since this is the NLP problem (Natural Language Processing), we used the BERT embeddings for text representations and classified the tickets with SVM (Support Vector Machine) algorithm. In essence, the algorithm has to read the customer’s ticket and based on the recognized text, it forwards it to the logistics support or the technical support deportment. The is achieving a balanced accuracy of more than 90% right now and we keep improving it. Priority of the tickets The second task for us was to determine the priority of the received ticket. Based on the text in the ticket, the model has to prioritize it and assign it to the employee, who is either the best qualified to solve it or who has the most suitable workload in order to solve the ticket in time. This is a typical regression problem, with ticked evaluation on scale from 1 to 100. The final result is a classification of the ticket into three priority groups. Distribution After this initial step, another process takes over and assigns the ticket to the agent, who is the most suitable to solve it in time. The solution has been in use for several months and it has drastically reduced the unnecessary workload of the customer support personnel. After initial mistrust, everybody are now taking the AI process for granted which is in the essence the sole purpose of such integrations. The model runs on the Microsoft Azure, currently still on Azure Virtual Machine and connects to the Zendesk with the use of the API interface.