One way to help a data science team innovate successfully

The Lazada Data Science team has paper lunches together every Friday. Usually, we discuss about new papers we read, new ideas and implementations we tried, etc. This past Friday, we invited some special guests from Aviva to discuss about our journeys in cultivating a data-driven culture and building data science into the organization.

Some can transition successfully from traditional actuarial statistics to customer-based data science—but most fail

One of the guests, who is in charge of technology, mentioned something interesting.

Aviva is very strong in what most would consider traditional aspects of data science involving risk, actuarial statistics, etc (it’s over 300 years old, and is the second oldest institution in England after the Bank of England—of course it’s good!).

However, as it tries to build new capabilities around understanding the customer better and customer analytics, Aviva found that not many of its data scientists could transition successfully.

Why? What distinguishes those who transition successfully from those who do not?

Being always on the lookout for features that distinguish a top performer from the rest, this piqued my interest. What was it that those people who transitioned successfully had/did, I asked.

Continue reading


Product Categorization API Part 3: Creating an API

This post is part 3—and the last—of the series on building a product classification API. The API is available for demo here. Part 1 and 2 are available here and here.

In part 1, we focused on acquiring the data, and cleaning and formatting the categories. Then in part 2, we cleaned and prepared the product titles (and short description) before training our model on the data. In this post, we’ll focus on writing a custom class for the API and building an app around it.

The desired end result is a webpage where users can enter a product title and get the top three most appropriate categories for it, like so.


Continue reading