How it works

Ople is unique in how it applies AI to data science, continuously optimizing algorithms and outcomes with each data set to deliver the most accurate and actionable insights. Ople’s speed and accuracy can be attributed to its unequaled deep learning system (BASS) which uses behavioral assimilation to learn from each model and data set. This enables Ople to automate many of the tedious processes that encumber data scientists.

Additionally, Ople’s automated high performance model training continuously improves and accelerates results, liberating data scientists to analyze the business problems rather than constantly tweak the technology. With, Data Science teams can spend more time on the actual business objectives rather than the plumbing.

Upload Data

Files are expected to be CSV with a header using the following column prefixes:

index column, excluded from training
numeric feature column
categorical feature column
target column, these are the columns you are trying to predict

Example header:

‘id, num1, num2, n_count, cat1, cat2, c_employed, target’

Validate Data

After uploading your data set, Ople processes the data and uses it to train the AI engine, map and generate preliminary results to assure a consistent data quality. From the preliminary results, you can validate that the automated results are meeting or exceeding your human expectations of accuracy.

Configure Optimization

Ople compares the model it generates to the leading industry standards in order to create a best of breed model for your data. According to the user defined criteria, Ople runs the validated data set through multiple industry leading, artificial intelligence models including an Ople generated model. Ople then compares the accuracy of the results from the industry leading models to the Ople generated model, analyzes the variables, learns from these models and generates an optimized Ople AI model.

Get Final Model In Production

With the validated data and the Ople AI optimized model, the model can be quickly deployed and start running against your data. This whole process can be done in a few minutes or a few days, depending on the complexity of the model and the quality of the data, much faster than the weeks that data scientists currently spend generating new models. The end result yields faster, more accurate results while freeing the data science team to rapidly create even more models to tackle additional business challenges.