Model selection (green revenue)
Model selection (green revenue)
The 15Rock Green revenue platform is powered by a family of models with different capabilities. These models are customized for specific use cases.
Our proprietary climate models can understand and model relationships between climate solutions and the companies implementing them.
We offer four main models with different levels of power suitable for different tasks.
Davinci is our most capable model that combines elements of other models and is constantly tuned to be the best for general use cases.
While Davinci is generally the most capable, the other models can perform certain tasks exceptionally well. For example, Picasso can perform many of the same tasks as Davinci, but will have a larger result set for you to get more results to review.
We recommend using Davinci while experimenting since it will yield the best results. Once you’ve got things working, we encourage trying the other models to see if you can improve results.
Soon you will be able to improve the other models’ performance by building your own custom models or using one of our partners.
Davinci is the most capable model family and can perform any task the other models can perform and often with the best balanced results. For applications requiring a lot of understanding of the content, Davinci is going to produce the best results. These increased capabilities require more compute resources, so Davinci is not as fast updated as the other models.
Another area where Davinci shines is in understanding the intent of text. Davinci is quite good at solving many kinds of logic problems and understanding the motives of a innovative solution. Davinci has been able to solve some of the most challenging mapping problems involving cause and effect.
Good at: Complex solution, cause and effect
Gogh is extremely powerful, yet very fast. While Davinci is stronger when it comes to analyzing complicated datasets accross using multiple factors, Gogh is quite capable for finding needle in hay stacks by being very specific for companies & solutions.
Good at: Finding specific solutions, complex classification, sentiment around solution/company
Picasso is very broad. It can process a very large amount of information on the solutions and companies. As a result, it scans a larger range to take into account more information.
Good at: Understanding the larger context of firms(works well with firms with many divisions)
Dali tries to blend Gogh and Picasso in a unique way by casting a wide net like Gogh but finding specifics into the solutions like Picasso.
Good at: Experimenting if you want to balance of Gogh and Dali before you dig into one of the models.
Finding the right model
Experimenting with Davinci or Dali is a great way to find out what the platform is capable of doing. After you have an idea of what you want to accomplish, you can stay with Davinci or Dali if you are happy with the results or move on to Gogh or Picasso if you want to optimize around its capabilities.
Currently the models operate independently from the parameters but in the future they may adjust dynamically depending on the other options you select when searching for green solutions.