Zeenk Launches TQL for Time-Series Analytics

In the US, eCommerce analytics company Zeenk has launched a tool called Time Query Language (TQL), which in combination with its existing Causmos open-source library aims to provide marketers with predictive and incremental value analytics for their Shopify and Amazon programs.

Set up last October, Zeenk delivers marketing and sales insights to Amazon third-party sellers, to help them optimize their financial performance and investment across all their advertising and sales channels. The platform was launched following the acquisition of marketing software vendor Nanigans' social media ad business by customer experience software firm Sprinklr.

Users of the new TQL tool can manipulate log, CPD, event database and other time-series data, and process billions of records for daily analytics and modeling using a Python-based modeling language. According to the firm, TQL offers an 'SQL like' declarative language, making it easy to understand, inspect, and change the assumptions and computational steps used in the analysis. Zeenk's Causmos uses TQL to create causal modeling training and test sets for modeling longitudinal heterogeneous treatment effects (LHTE), supporting models for pre-post, uplift, difference-in-differences, AB-test/randomized controlled trials, and their longitudinal generalizations in both discrete and continuous time. Modeling software such as H20, TensorFlow and PyTorch can then be used for estimating causal modeling parameters.

Both solutions will be free to the data science and analytics research community for non-commercial research and commercial evaluation. CEO Brian Eberman (pictured) comments: 'We are pleased to make this technology available as open-source to the data scientist and research community. This will allow them to accelerate the speed of analysis for a wide range of time-series analysis problems'.

Web site: www.zeenk.com .

All articles 2006-23 written and edited by Mel Crowther and/or Nick Thomas, 2024- by Nick Thomas, unless otherwise stated.