17546564. RISK ADAPTIVE ASSET MANAGEMENT simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)
Contents
RISK ADAPTIVE ASSET MANAGEMENT
Organization Name
INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor(s)
Tetsuro Morimura of Shinagawa-ku (JP)
RISK ADAPTIVE ASSET MANAGEMENT - A simplified explanation of the abstract
This abstract first appeared for US patent application 17546564 titled 'RISK ADAPTIVE ASSET MANAGEMENT
Simplified Explanation
The abstract describes a computer-implemented method for supply chain management. Here are the key points:
- The method uses a feature vector to analyze supply chain delivery trends, a given portfolio of items, and the current investment amount.
- It determines whether the current supply chain delivery situation is normal or abnormal based on the feature vector.
- If the situation is abnormal, a risk-avoidance action is performed to reduce the investment amount and avoid potential delivery losses.
- If the situation is normal, a risk adaptive action is performed to increase the investment amount and potentially gain from supply chain deliveries using a distributional reinforcement learning process.
Potential Applications
This technology can be applied in various industries and sectors that rely on supply chain management, including:
- Manufacturing: Optimizing inventory levels and investment decisions based on supply chain delivery trends.
- Retail: Managing stock levels and investment strategies to minimize losses and maximize gains.
- Logistics: Improving decision-making for transportation and distribution based on supply chain data.
- E-commerce: Enhancing order fulfillment and inventory management processes for online retailers.
Problems Solved
The technology addresses several challenges in supply chain management, such as:
- Uncertainty: By analyzing supply chain delivery trends, it helps identify abnormal situations and take appropriate actions to mitigate potential losses.
- Risk management: The risk-avoidance and risk adaptive actions help balance investment decisions and optimize outcomes based on the current supply chain situation.
- Decision-making: The use of a feature vector and reinforcement learning process provides a data-driven approach to make informed decisions in supply chain management.
Benefits
Implementing this technology offers several benefits for supply chain management:
- Improved efficiency: By analyzing supply chain delivery trends, it enables proactive decision-making and reduces the likelihood of disruptions or losses.
- Cost savings: The risk-avoidance action helps minimize potential losses, while the risk adaptive action allows for capitalizing on favorable supply chain situations, leading to overall cost savings.
- Enhanced decision-making: The use of data-driven analysis and reinforcement learning improves the accuracy and effectiveness of investment decisions in supply chain management.
Original Abstract Submitted
A computer-implemented method is provided for determining an action with respect to a given portfolio of items for supply chain management. The method includes acquiring, by a hardware processor, a feature vector for supply chain delivery trends, the given portfolio, and a current investment amount. The method further includes determining, by the hardware processor, whether a current supply chain delivery situation is normal or abnormal based on the feature vector. The method also includes performing a risk-avoidance action to reduce the current investment amount and avoid potential supply chain delivery losses, responsive to a determination that the current supply chain delivery situation is abnormal. The method additionally includes performing a risk adaptive action to increase the current investment amount and incur potential supply chain delivery gains by using a distributional reinforcement learning process, responsive to a determination that the current supply chain delivery situation is normal.
