natural language processing Finding frequently asked questions in Google with Natural Language Processing It's pretty clear that Google searches are a key way people find businesses. 35% of referral traffic comes from search, versus 26% from social, a difference that appears to be growing.
Interactive Visualization Visualizing business categories across Facebook, Yelp and Google In the process of building business profiles on social media platforms, choosing the right businesses categories plays critical role as it helps potential customers find the business right away. However, the task is
models Talks on probabilistic modelling from tech @ ThriveHive In the past month or so we've been giving talks and workshops on one of our projects to predict customer spend on different digital marketing services. Briefly, the project aimed to use
models Interpreting machine learning models: Picking low-hanging business insights, Part 3: Getting results In the previous blog posts we talked about interpretability in machine learning and how to set up your machine learning question. We also discussed a bit about the application to ThriveHive's data.
models Interpreting machine learning models: Picking low-hanging business insights, Part 2: Asking questions Interpreting machine learning models: Picking low-hanging business insights Part 2: Asking questions In the previous blog post we examined the importance of interpretability in machine learning models and how to interpret the parameters
models Interpreting machine learning models: Picking low-hanging business insights, Part 1: Linear thinking ThriveHive has been putting out a couple of exciting infographics based on some of our work here on the Data Science team. I thought it might be worthwhile to dig into the
natural language processing Identifying product mix, part 2: Implementation In the previous post, we outlined one of the major challenges facing analytics here at ThriveHive; segmenting a business population that may not fall neatly into existing classification systems. We came up
natural language processing Identifying product mix: A bottom-up approach to segmenting a small business population Part 1: Set up Typically methods for segmenting businesses have relied on standardized industry classification systems (e.g. NAICS). However, the limitation of a top-down industry classification system is that it does
social media What are the major social traffic drivers for ThriveHive small businesses? Small businesses (those employing less than 500 people) make up the majority of firms (>99%) and the majority of new jobs created in the last 10 years. As such, they're
commentary Two Myths, Debunked: Why Data Analytics isn’t just for Big Business We're already two months into 2018, so this isn't one of those new year crystal ball prediction blogs. Let's all agree to leave those in the rearview for at least another 10 months!
natural language processing How the Words Used in Email Subject Lines Relate to Open Rates Previously, we found that the association between subject line length and email open rate varies by industry. In this blog post, I will use the same generalized linear model (GLM) to examine
email What Impact Do Email Subject Lines Length Have on Open Rates? Previously, we found that ThriveHive customers' email campaigns achieve open rates significantly higher than the industry standard. This difference, however, varies by industry. For example, Computers & Electronics and Entertainment & Events
news How Do ThriveHive Users’ Email Marketing Stats Compare with Industry Standards? Despite the proliferation of social media sites and connected apps, email still remains the marketing channel with the highest return on investment. According to the Direct Marketing Association, email has a median ROI