ML Task Completion Scoring via Data Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users of task databases, such as CRM systems, face challenges in predicting the likelihood of task completion based on available data, which is crucial for forecasting sales revenues and identifying at-risk opportunities.
Innovation Solution
A system and method for training machine learning models to generate real-time scores predicting task completion probabilities, utilizing a workflow with stages like preprocessing, segmentation, downsampling, feature selection, and training, and employing models like Random Forest, Xgboost, and LSTM, with a user-configurable interface for feature and workflow settings, allowing for real-time data processing and accurate prediction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning models are trained to predict task completion probabilities, then prediction accuracy is improved, but system complexity increases
Solution Approach 1:
The patent segments the task completion prediction problem into multiple independent machine learning models, each trained on specific subsets of features and data. This allows the system to achieve high prediction accuracy through specialized models while managing complexity by dividing the overall prediction task into manageable segments that can be developed, trained, and maintained independently.
2Reliability
If multiple machine learning models are employed for different segments, then prediction reliability is improved, but computational resources increase
Solution Approach 1:
The patent implements a segmented modeling approach where multiple machine learning models are trained on different subsets of features and data segments. Each model focuses on specific aspects of task completion prediction, achieving high reliability for its domain while avoiding the computational overhead of training a single comprehensive model on all data. This partial action principle allows the system to distribute computational resources efficiently across multiple specialized models rather than concentrating all resources in one large model.
Data Source
AI summary
According to various embodiments, described herein are systems and methods for training machine learning (ML) models to generate real-time scores to predict the probabilities of task completion. In one embodiment, an exemplary method includes the operations of receiving, from a data store, a set of features and a workflow for training a first type of ML models, the workflow specifying a data source, a number of stages and associated parameters for training the ML models; retrieving, from the data source, training data for the set of features; and segmenting the training data into different segments. The method further includes the operations of training a separate first type of ML model using each of the different segment of the training data in accordance with the workflow; and persisting the first type of trained ML models into the data storage. The method also includes using a trained ML model to generate probability scores and displaying the scores to users in real-time.