Good AI Vibes #8
Perfecting Brand-Celebrity Fits, Ensuring Blood Supply Efficiency, and Pioneering in Tissue Paper Logistics
π Hello and welcome back to another edition of Good AI Vibes! π
We're thrilled to bring you a fresh issue of inspiring AI applications that are reshaping businesses and industries alike. Whether you're a seasoned AI enthusiast or a newcomer keen on learning about the innovative potential of artificial intelligence, Good AI Vibes is your go-to source for the most exciting and transformative AI applications. π
Haven't joined our growing community of AI enthusiasts yet? Just hit the subscribe button below.
Each issue, we carefully curate 3 ground-breaking applications of AI, each unraveling unique challenges and ingenious solutions across various sectors. In this eighth edition of Good AI Vibes, we're particularly excited to bring you these thought-provoking stories:
π€ The Twitter Approach to Brand-Celebrity Compatibility (Industry: Retail, Consumer Services & Travel / Business Function: Marketing, Sales & Customer Relations)
π©Έ When Every Drop Counts: AI's Role in Optimizing Blood Supply Chains (Industry: Public Sector & Essential Services / Business Function: Supply Chain, Logistics & Sustainable Operations)
π¦ Breaking the Box: How AI Enhanced Tissue Paper Logistics (Industry: Industrial Manufacturing, Transportation & Logistics / Business Function: Supply Chain, Logistics & Sustainable Operations)
These stories demonstrate how AI is not just a technological marvel, but a transformative tool that is creating ripples of change in industries worldwide.
For those of you who've already stepped up your AI game with our premium subscription π, you'll continue to enjoy an additional 3 use cases per issue, tailored to your industry or business function. Additionally, your premium subscription grants you access to our extensive use-case database, designed with user-friendly search and filtering options to help you easily unearth the insights most relevant to you. π π
If you haven't upgraded to our premium subscription yet, consider joining our league of AI frontrunners today. π By upgrading, you not only support our work, but you also ensure that you remain at the forefront of AI advancements with premium insights tailored just for you. To upgrade your subscription and unlock these exclusive benefits, click the button below.
Now, let's explore the AI journeys that are shaping new paradigms in diverse industries.
Happy reading, everyone! π βοΈ
The Twitter Approach to Brand-Celebrity Compatibility
What's the critical hurdle?
Consider the situation of Danielle, the Brand Manager of a burgeoning fashion label. The challenge she faced was not unique but central to her role: deciding which celebrity would endorse her brand effectively. The power of a celebrity endorsement relies heavily on the perceived compatibility between the celebrity and the brand - the brand-celebrity fit. However, with evolving trends, diverse consumer opinions, and numerous potential celebrities, determining this fit is a labyrinthine task. Making the wrong decision could jeopardize brand image and result in significant financial loss.
How was this initially tackled?
In the past, Danielle relied heavily on traditional market research techniques to inform her decisions. Focus groups, surveys, and demographic profiling were all part of her toolkit. These methods provided insights into the perceived image of potential celebrities and how they might align with the brand. In essence, she was banking on the consumers' subjective judgments and responses to get a picture of what the ideal celebrity-brand fit would be.
Why did the initial approach fall short?
Despite their usefulness, these traditional market research methods proved to be time-consuming, expensive, and sometimes unreliable. The responses gathered from such methods could be biased or influenced by the immediate mood or environment of the participants, and they didn't always translate accurately to the wider consumer base. Moreover, with the rapidly changing nature of consumer trends and celebrity status, these insights could quickly become outdated. The process lacked the flexibility and agility to keep up with the fast-paced world of brand endorsements.
How did AI revolutionize the solution?
Seeing the need for a new solution, Danielle decided to turn to AI, specifically leveraging its diagnose capabilities. She focused on Twitter lists, user-curated collections of accounts often grouped by shared interests or affiliations. Danielleβs team developed a metric using AI to analyze the frequency of co-listings of a brand and a celebrity. This metric served as an indicator of the perceived association between them. The idea was simple but powerful: if Twitter users frequently grouped a celebrity and a brand together, it was likely that they perceived a strong connection between the two, suggesting a good fit for endorsement. This innovative use of AI allowed Danielle to automate the massive task of combing through Twitter lists and provided a direct, user-centric measure of brand-celebrity fit. Unlike traditional methods relying on time-consuming surveys or expert assessments, this AI-powered approach was not only more efficient and scalable but also potentially more accurate. By integrating AI, Danielle opened the door to identifying fitting celebrity endorsements for brands in a whole new way.
Main reference: Saridakis, C., Katsikeas, C. S., Angelidou, S., Oikonomidou, M., & Pratikakis, P. (2023). Mining Twitter lists to extract brand-related associative information for celebrity endorsement. European Journal of Operational Research. Volume 311, Issue 1, 16 November 2023, Pages 316-332.
See other references at the end.
When Every Drop Counts: AI's Role in Optimizing Blood Supply Chains
What's the critical hurdle?
Meet Adrian, a health logistics manager responsible for the functioning of a vast network of blood collection and distribution centers. The problem that kept Adrian awake at night was the persistent blood shortages they faced. Managing the blood supply chain was a juggling act: between the intricate decision-making of blood collection, routing, location of collection stations, inventory management, and the overarching objective of meeting the blood demand. Failing to make the right decisions not only led to spiraling costs but also endangered patients' lives β a burden too heavy to bear for Adrian.
How was this initially tackled?
Traditionally, the approach to blood collection and distribution involved separate decision-making processes for each issue - from identifying collection station locations to routing and inventory management. Decisions were often based on historical data and intuition. However, as the complexity of the blood supply chain grew, Adrian recognized that this fragmented, reactive strategy was inadequate. It lacked precision and failed to consider the holistic nature of the supply chain, where a decision in one area can significantly impact others.
Why did the initial approach fall short?
The traditional approach was deficient in two critical ways: it lacked the capability to adequately handle conflicting objectives and was insufficiently precise. Balancing the cost-effectiveness of operations with the goal of minimizing blood shortages was a constant struggle. Furthermore, every decision, whether about collection station location or blood quantity collection, held the potential to influence the entire supply chain, thus amplifying the need for precision. The absence of an integrated, precise decision-making model caused escalating costs, persistent blood shortages, and even risked patient lives.
How did AI revolutionize the solution?
The turning point arrived when a novel AI-based solution was introduced. A bi-objective model was developed that allowed a more accurate and integrated approach to decision-making. It provided a unified approach to decision-making in various aspects and precisely determined the location of blood collection stations, whether permanent or temporary, and managed the transshipment and inventory of the blood center. It also worked out the optimal routes for blood transportation and the ideal quantity of blood to be collected. This AI solution was not only successful in addressing the unique challenges faced by Adrian but also set a new benchmark in managing blood supply chains. It was reported that designing the network using this mathematical model significantly reduced total blood costs and shortages. Adrian, like many health logistics managers, now has a precise, integrated, and efficient tool at his disposal, revolutionizing how blood supply chains are managed.
Main reference: Esmaeili, S., Bashiri, M., & Amiri, A. (2023). An exact criterion space search algorithm for a bi-objective blood collection problem. European Journal of Operational Research. Volume 311, Issue 1, 16 November 2023, Pages 210-232.
See other references at the end.
Breaking the Box: How AI Enhanced Tissue Paper Logistics
What's the critical hurdle?
Meet Sofia, a logistics manager at a leading tissue paper manufacturing company. Every day, she found herself tackling an intriguing, yet daunting challenge: efficient packing of tissue paper rolls for shipping. With these products being of low density, volume, rather than weight, became the key factor in logistics decisions. However, the susceptibility of these products to deformation during packing posed an additional layer of complexity. This characteristic of tissue paper was typically overlooked in the packing process, leading to inefficiencies and product damage - issues that constantly beleaguered Sofia in her role.
How was this initially tackled?
Sofia's initial solution was an established yet simple one: a rule-based packing system. This system primarily focused on maximizing the volume utilization of the shipping pallets. It involved arranging the tissue rolls in a way that would occupy the most space while causing minimal deformation. Rules were established based on product dimensions and placement strategies. For instance, heavier rolls would be placed at the bottom to provide a stable base, and lighter ones were added to the top. Despite its simplicity, this method did serve a purpose by providing a structured approach to the packing process.
Why did the initial approach fall short?
The fundamental issue with the traditional rule-based system, however, was its static nature. It failed to account for the dynamic and complex realities of packing low-density and easily deformable tissue paper rolls. For one, it overlooked the fact that different tissue products could deform differently under the same conditions. Secondly, it did not consider the cumulative effect of deformation as more and more products were added to the pallet. This resulted in less-than-optimal packing strategies and made the packing process more of a trial-and-error endeavour rather than a precise, predictable operation. Furthermore, the system lacked the ability to learn from previous packing operations and adapt accordingly - a major drawback given the diverse range of tissue paper products and the variability in their deformation characteristics. Over time, these limitations led to a significant reduction in packing efficiency and an increased risk of product damage.
How did AI revolutionize the solution?
The real breakthrough occurred when AI was used to model the deformation of tissue paper during the packing process. This novel approach enabled the creation of an adaptive packing strategy, one that could factor in the variables of the packing process and the unique characteristics of the tissue paper. AI's knack for recognizing patterns in vast amounts of data meant that it could accurately predict the deformation and adjust the packing policy accordingly. Not only did this methodology prove resilient against uncertainty, but it also increased load density by 4-7% on average in the worst-case scenario. Most remarkably, when tested under optimal configurations, this approach even achieved a whopping 40% increase in load density. Hence, AI not only solved the issue at hand but also set a new benchmark in packing efficiency for tissue paper products, paving the way for significant cost savings in logistics.
Main reference: Coutinho, J. P. L., Reis, M. S., Neves, D. F. M. G., & Bernardo, F. P. (2023). Robust optimization and data-driven modeling of tissue paper packing considering cargo deformation. Computers & Industrial Engineering. Volume 175, January 2023, 108898.
See other references at the end.
Good AI Vibes Cartoons π
Let's sprinkle some AI humor into your day! Get set for the next 'Good AI Vibes Cartoonβ! π
Came across an amusing AI misconception in your conversations? Share the story in the comments. π¬ π
Thank you for journeying with us through the eighth issue of Good AI Vibes!
Sharing is caring, as we say, especially when it comes to knowledge! Don't hesitate to pass along this newsletter to colleagues, friends, or anyone you believe would enjoy and benefit from these AI vibes. Together, we'll make the AI journey more fruitful and fun. π
We appreciate and welcome your feedbackβit's the compass that helps us navigate towards better content. Feel free to share your thoughts, ideas, or even AI-related humor with us at hello@goodaivibes.com. π
Remember, Good AI Vibes isn't just a biweekly newsletterβit's a thriving community of AI enthusiasts! Make sure to follow us on social media for more regular AI insights and engaging discussions. For more comprehensive information, we welcome you to visit our website.
Until the next issue, keep the AI vibes buzzingβ¦ See you next time! π