---
title: Use cases and horizontal approaches
description: Applied approaches to specific business challenges and general frameworks for broad classes of machine learning problems.

---

# Use cases and horizontal approaches

Topic | Describes... |
----- | ------ |
[Cold start demand forecasting workflow](cold-start) | This accelerator provides a framework to compare several approaches for cold start modeling on series with limited or no history.
[End-to-end time series demand forecasting workflow](demand-flow) | Perform large-scale demand forecasting using DataRobot's Python package.
[Deploy a model in AWS SageMaker](deploy-sagemaker) | Learn how to programmatically build a model with DataRobot and export and host the model in AWS SageMaker.
[Demand forecasting and retraining workflow](df-retrain) | Implement retraining policies with DataRobot MLOps demand forecast deployments. |
[Predictions for fantasy baseball](fantasy-baseball) | Leverage the DataRobot API to quickly build multiple models that work together to predict common fantasy baseball metrics for each player in the upcoming season. |
[Use Gramian angular fields to improve datasets](gramian) | Generate advanced features used for high frequency data use cases.
[Tackle churn before modeling](ml-churn) | Discover the problem-framing and data management steps required to successfully model for churn, using a B2C retail example and a B2B example based on a DataRobot’s churn model. |
[Mastering tables in production ML](ml-tables) | Review an AI accelerator that uses a repeatable framework for a production pipeline from multiple tables.
[Netlift modeling workflow](ml-uplift) | Leverage machine learning to find patterns around the types of people for whom marketing campaigns are most effective. |
[Use feature engineering and Visual AI with acoustic data](ml-viz) | Generate image features in addition to aggregate numeric features for high frequency data sources. |
[Demand forecasting with the What-if app](ml-what-if) | Discover the problem framing and data management steps required to successfully model for churn, using a B2C retail example and a B2B example based on a DataRobot’s churn model. |
[No-show appointment forecasting](no-show) | How to build a model that identifies patients most likely to miss appointments, with correlating reasons. |
[Predict factory order quantities for new products](pred-products) | Build a model to improve decisions about initial order quantities using future product details and product sketches.  |
[Build a recommendation engine](rec-engine) | Explore how to use historical user purchase data in order to create a recommendation model, which will attempt to guess which products out of a basket of items the customer will be likely to purchase at a given point in time. |
[Use self-joins with panel data to improve model accuracy](self-joins) | Explore how to implement self-joins in panel data analysis. |
[Create a trading volume profile curve with a time series model factory](ts-factory) | Use a framework to build models that will allow you to predict how much of the next day trading volume will happen at each time interval. |
