Neural Information Processing Systems http://nips.cc/

Transportation cost is an attractive similarity measure between probability distributions due to its many useful theoretical properties. However, solving optimal transport exactly can be prohibitively expensive.

Labor market forecasting on talent demand and supply is essential for business management and economic development. With accurate and timely forecasts, employers can adapt their recruitment strategies to align with the evolving labor market, and employees can have proactive career path planning according to future demand and supply. However, previous studies ignore the interconnection between demand-supply sequences among different companies and positions for predicting variations. Moreover, companies are reluctant to share their private human resource data for global labor market analysis due to concerns over jeopardizing competitive advantage, security threats, and potential ethical or legal violations. To this end, in this paper, we formulate the Federated Labor Market Forecasting (FedLMF) problem and propose a Meta-personalized Convergence-aware Clustered Federated Learning (MPCAC-FL) framework to provide accurate and timely collaborative talent demand and supply prediction in a privacy-preserving way. First, we design a graph-based sequential model to capture the inherent correlation between demand and supply sequences and company-position pairs. Second, we adopt meta-learning techniques to learn effective initial model parameters that can be shared across companies, allowing personalized models to be optimized for forecasting company-specific demand and supply, even when companies have heterogeneous data. Third, we devise a Convergence-aware Clustering algorithm to dynamically divide companies into groups according to model similarity and apply federated aggregation in each group. The heterogeneity can be alleviated for more stable convergence and better performance. Extensive experiments demonstrate that MPCAC-FL outperforms compared baselines on three real-world datasets and achieves over 97% of the state-of-the-art model, i.e., DH-GEM, without exposing private company data.

Most businesses have digitally transformed their workflows and are exploring innovative ways to ensure they have robust digital end-to-end supply chains to improve their efficiency. Irrespective of the strategies embraced, modern supply chain management heavily depends on effective demand planning strategies. One of the top priorities of every organization should be developing a supply chain with utmost efficiency to minimize errors. Business leaders that want to manage demand and supply efficiently need to have the best strategies and tools for demand planning and forecasting. Leveraging the best demand planning and forecasting tools in the IT infrastructure will help businesses to minimize the risks and enhance the product, services, and information flow and deliver a top-notch customer experience.

ArtificiaI Intelligence or AI is having a major impact on the world of journalism, allowing journalists to better keep up with the ever-changing and growing amounts of news. AI technology is able to quickly sort through data and provide more accurate and timely news stories and insights that would have otherwise been impossible to uncover. This technology is helping journalists stay ahead of the curve, ensuring that news stories are as accurate and relevant as possible. To demonstrate how journalists can use AI in their work, blockchain developer and MB Tech consultant Alvin Veroy created this story using Artificial Intelligence with a very minimal human intervention. And by the way, AI also created this introduction and the image. In recent years, blockchain and cryptocurrency have become increasingly popular among tech-savvy investors, startups, and large corporations alike.

"Produce better-quality products but at less operational cost and with efficiency" is a timeless goal for the manufacturing industry. The role and future of AI and ML in the manufacturing industry are promising. AI and ML can enable the manufacturing industry to scale their businesses and help them grow. The "Smart Manufacturing" revolution is already making it easier for businesses to attain this objective than ever before. According to many experts, artificial intelligence and machine learning are expected to affect factories and the manufacturing sector in the future significantly.

The e-commerce industry has evolved into one of the most competitive and crowded spaces. With so many e-commerce platforms to choose from, retaining the customer in your business is becoming all the more difficult by the day. Thankfully, we have technological advancements that can help you better serve your customers and grow your business. Yes, we are talking about machine learning in e-commerce. Machine learning is a subset of artificial intelligence that has created immense value for retailers today.

The COVID-19 pandemic has been sort of an eye-opener for the logistics industry. Shattering and uprooting the supply chains, shaking up the dynamics of demand and supply, and exposing the vulnerabilities of the entire logistics ecosystem, the pandemic has done it all. Some of the supply chains that successfully survived the tough times were the ones that already had the new-age, smart technologies embedded into each and every aspect of their operations. The ones that succumbed to the crisis were those who had not taken the journey to complete digitization. Perhaps, no one had anticipated the advent of something like this ever before. Now, with the waves of disruption slowly settling logistics firms are now actively on the hunt for creative ways to optimize their operations, in order to drive maximum productivity and growth.

The use of artificial intelligence (AI) in inventory management can help remove the inefficiencies in the current processes by enabling a predictive approach and reducing errors by automating operations. The current inventory management practices are laced with challenges and inefficiencies. Inventory management is mostly done manually, and thus takes a lot of time. Similarly, there is a high chance of error that can impact business operations. This can lead to customer complaints due to the gap between demand and supply which is usually caused by incorrect information input. As a result, deliveries to customers are delayed, which can lead to businesses losing out on customers and facing reputational losses.

LLamasoft published the results of a global retail supply chain study, which revealed that 73% of retailers believe artificial intelligence (AI) and machine learning can add significant value to their demand forecasting processes. Meanwhile, over half say it will improve 8 other critical supply chain capabilities. The research also found that while 56% of overperforming retailers, also known as'retail winners', use technology to model contingency plans for severe supply chain interruptions, a mere 31% of retailers who are not overperforming do the same. Overall, 56% of retailers surveyed are struggling with the ability to respond to rapid shifts, and the lack of flexibility has cost them during the disruptions such as COVID-19, with many seeing a huge drop in revenue as a result. In addition, 73% of'retail winners' have the foresight and ability to monitor capacity, which allows them to prepare for sudden shifts in demand and supply, compared to 35% of'other' or'under-performing' retailers.