Sales Activity Support Apparatus Balancing Exploration and Track Records
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sales activity support systems struggle to effectively balance exploratory and established sales strategies, leading to increased burdens on sales representatives and reduced short-term sales performance when focusing on new client development, as policies generated by reinforcement learning may not align with past experiences and knowledge.
Innovation Solution
A sales activity support apparatus and method that calculates a predicted value of KPIs using a learned prediction model, determines a policy value by weighting upward deviations in track record values, and outputs both weighted and unweighted policy values to balance exploratory and established sales activities, allowing for explicit positioning and understanding by sales representatives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If reinforcement learning is used to generate sales activity policies, then new client development and long-term growth are improved, but short-term sales performance and sales representative burden increase
Solution Approach 1:
The system dynamically adjusts policy recommendations based on the sales representative's past performance data and track records. By learning from historical data, the system adapts its recommendations to match the individual representative's strengths and tendencies, making the policy dynamic rather than static. This allows the system to balance exploratory new client development with established successful patterns, resolving the contradiction between innovation and short-term performance.
Solution Approach 2:
The system incorporates feedback loops where sales representatives' past actions and results are continuously analyzed to refine future policy recommendations. The reinforcement learning model uses feedback from track record data to adjust and improve its recommendations over time, ensuring that new client development strategies are informed by actual performance outcomes rather than theoretical models alone.
2Adaptability or versatility
If reinforcement learning generates sales policies, then exploratory sales strategies are improved, but alignment with past experiences and knowledge deteriorates
Solution Approach 1:
The system merges reinforcement learning-generated policies with historical track record data by training the model on past sales representative behaviors and outcomes. This combination integrates the exploratory capabilities of reinforcement learning with the stability and reliability of established past experiences, creating hybrid policies that both innovate and respect historical success patterns.
Solution Approach 2:
The system performs preliminary analysis of the sales representative's past track records before generating policy recommendations. By pre-processing and understanding historical data in advance, the system ensures that new exploratory strategies are grounded in the representative's proven experience and knowledge, maintaining alignment while enabling innovation.
3Adaptability or versatility
If focus is placed on new client development, then long-term growth is improved, but sales representative burden and short-term performance worsen
Solution Approach 1:
The system enables sales representatives to self-serve by providing personalized policy recommendations that leverage their own past successful patterns. The reinforcement learning model analyzes each representative's unique track record and generates tailored guidance, reducing the burden of manual analysis and decision-making while maintaining alignment with their proven effective strategies.
Solution Approach 2:
The system changes the parameters of policy recommendations based on individual representative characteristics and historical performance. By adjusting recommendations to match each representative's specific profile and past successes, the system makes new client development more manageable and less burdensome, as the guidance is customized rather than generic.
Data Source
AI summary
A sales activity support apparatus 100 is configured including a storage device 101 that holds pieces of information on a sales target organization and a sales activity and an arithmetic device 104 that calculates a predicted value of a KPI by applying information in the pieces of information other than part of the pieces of information to a KPI prediction model, calculates a weight corresponding to a degree by which the predicted value exceeds a track record value for the sales activity, generates a policy value determination model through learning based on the organization information, the KPI, and the weight, determines the policy value by applying the organization information to the determination model, determines an unweighted policy value by applying the organization information to a determination model learned with no weight applied, and outputs them.