Update README.md

README.md

@@ -4,7 +4,7 @@
 
 Bootstrap your large-scale forecasting solutions on Databricks with the Many Models Forecasting (MMF) Solution Accelerator.
 
-MMF accelerates the development of sales and demand forecasting solutions on Databricks, including critical phases of data preparation, training, backtesting, cross-validation, scoring, and deployment. Adopting a configuration-over-code approach, MMF minimizes the need for extensive coding. But with its extensible architecture, MMF allows technically proficient users to incorporate new models and algorithms. We recommend users to read through the documentation and the source code, and modify it to their specific requirements. 
+MMF accelerates the development of sales and demand forecasting solutions on Databricks, including critical phases of data preparation, training, backtesting, cross-validation, scoring, and deployment. Adopting a configuration-over-code approach, MMF minimizes the need for extensive coding. But with its extensible architecture, MMF allows technically proficient users to incorporate new models and algorithms. We recommend users to read through the source code, and modify it to their specific requirements.
 
 MMF integrates a variety of well-established and cutting-edge algorithms, including [local statistical models](https://github.com/databricks-industry-solutions/many-model-forecasting?tab=readme-ov-file#local-models), [global deep learning models](https://github.com/databricks-industry-solutions/many-model-forecasting?tab=readme-ov-file#global-models), and [foundation time series models](https://github.com/databricks-industry-solutions/many-model-forecasting?tab=readme-ov-file#foundation-models). MMF enables parallel modeling of hundreds or thousands of time series leveraging Spark's distributed compute. Users can apply multiple models at once and select the best performing one for each time series based on their custom metrics.