Understanding your needs

 

In our introductory meeting, we will get familiar with your needs, collect initial information, and define minimum data quality requirements. After we get sample datasets meeting those requirements, we will follow up with a draft of a proposal.

 

We follow an agile development process which means that we will be checking with you early and often to communicate next steps and feasibility of your project. Well defined goals and data pre-assessment help the data science team to change approaches, refine hypothesis and even discard the project if the business case is non-viable or the benefits from the predictive models are not worth the effort to build it.

 

Data Discovery

Once we establish your goals and assure the viability of the data, we will spend two to six weeks working with your data discovering patterns and stories behind it, and proving the hypothesis. At this time our data science team will identify approaches and technology stack best applicable to your case.

 

Rely on trading software to keep you ahead of regulatory concerns so you can respond more quickly to opportunities while maintaining a focus on profitability.

 

Data Transformation

This step involves cleaning the data and reshaping it into a readily usable form for performing data science. This is similar to the traditional ETL steps in data warehousing in certain aspects, but involves more exploratory analysis and is primarily aimed at extracting features in usable formats.

 

Hypothesis and modeling

Hypothesis and modeling are the traditional data mining steps - however, in a data science project, these are not limited to statistical samples. Indeed the idea is to apply machine learning techniques to all data. A key sub-step is performed here for model selection. This involves the separation of a training set for training the candidate machine-learning models, and validation sets and test sets for comparing model performances and selecting the best performing model, gauging model accuracy and preventing over-fitting.

​

Deliverables: models, processes and Insights

Once our consultants came with an optimal model, we can either train your team to maintain it going forward or continue working with you on optimization processes and developing further insights