Deep reinforcement learning for supply chain and price optimization
A hands-on tutorial that describes how to develop reinforcement learning optimizers using PyTorch and RLlib for supply chain and price management....Learn more
At Grid Dynamics, our mission is to improve the operational efficiency of our clients using state-of-the-art machine learning methods. We work with various enterprise use cases including customer intelligence, supply chain and revenue management, and risk management. In the area of advanced customer intelligence analytics, we extensively use deep learning, reinforcement learning, natural language processing methods, sentiment analysis, pattern recognition, and omnichannel marketing models. In the area of pricing and revenue management in supply chain, we focus on deep learning and reinforcement learning algorithms, econometric supply chain pricing models, combinatorial optimization, and other techniques that help to increase supply chain pricing power and improve supply chain pricing strategy. We also work with computer vision algorithms and applications, as well as natural language processing models to develop advanced information retrieval and document processing services. This part of our Insights portal presents our research, analytics, and case studies on these topics in a systematic way.
We focus on the learning of useful semantic representations (embeddings) for products and customers using neural networks. We show that many of these representation learning tasks can be efficiently accomplished using standard natural language processing (NLP) methods....Learn more
Mr and Mrs. Smith are a regular middle-class couple in the process of remodeling and redecorating their home. After a long and tireless search on Pinterest and other lifestyle websites, they finally found a concept for their new interior decoration plans. The only issue was that actually finding and buying...Learn more
Read the article where described the Grid Dynamics machine learning domain specific language (ML-DSL) library. It is used with Jupyter notebooks to simplify the data scientist’s experience of interacting with cloud platforms (Amazon AWS, Google Cloud Platform) to implement ML/DS pipelines....Learn more