5000 Executive Parkway, Suite 520, San Ramon, CA 94583
Supply chain optimization is a complex problem that involves multiple layers, products, time periods, resource constraints, and uncertainties. In this article, the authors explore how reinforcement learning (RL) can be used to optimize inventory and pricing decisions in a supply chain. They develop a simulation environment and a deep RL model that learns how to make these decisions.
This report discusses the priorities, challenges, and plans of marketing and merchandising executives in implementing decision automation in revenue management, including the use of AI/ML technologies, tools and capabilities needed, barriers to adoption, and readiness to try new optimization tools.
This white paper provides practical guidance for business and technology executives on adopting AI, including case studies on promotion targeting, customer intelligence, promotion price optimization, safety stock, and product information management.
This white paper offers practical advice for technology and business leaders on how to use advanced data analytics and engineering capabilities to respond effectively to the disruptions caused by COVID-19. The recommendations are based on early examples of successful response actions taken by various industries.
This white paper discusses the design of a price intelligence platform that utilizes data science and machine learning to provide decision support and automation for pricing analytics and revenue management.
This report provides an overview of recent advances in customer intelligence by examining 10 industrial case studies, covering topics such as deep learning models, reinforcement learning models, and econometric models used in marketing analytics.
This article provides practical recommendations for business leaders on how to leverage advanced data analytics and engineering capabilities to respond to the disruptions caused by the COVID-19 pandemic. It emphasizes the importance of agility, customer engagement, and supply chain optimization in navigating through this challenging time.
This article discusses the use of neural networks and NLP methods for personalization and recommendation algorithms. It explores the learning of semantic representations for products and customers using techniques such as item2vec and customer2vec, and provides case studies and a hands-on tutorial using a public dataset of Instacart orders.
This article explores how deep reinforcement learning methods can be applied in supply chain and price management scenarios, providing hands-on tutorials and examples using PyTorch and RLlib.
The article discusses the problem of marketing spend optimization and how deep learning methods can be used to analyze sequences of customer interactions and optimize marketing budgets. The article explores different attribution models, including last-touch attribution, logistic regression, LSTM, and LSTM with attention. The models are evaluated using a simulation algorithm that replays historical events and estimates the number of conversions based on the budget allocation. The results show that the LSTM with attention model provides the best budget allocation.
