Tutorial: Getting alternative data for research

equity research

What is alternative data for research?

Data is the basis for all sound research models. Alternative data along with traditional data ensures a complete picture and allows modeling of future events. Alternative data includes information that is publicly available on the internet, but often difficult to get in a structured, easy to digest format.

Alternative data can include:

  • Retail price changes across vendors
  • Store closures and openings
  • Consumer sentiment ratings
  • Influencer opinions in blogs and forums
  • Local and world news
  • Weather and micro-climates

How can Import.io help?

Import.io extracts data from alternative sources such as industry blogs, social media sites, social news aggregation sites, ecommerce and travel aggregators, retail sites, and just about any website. Data extraction can be scheduled hourly, daily, weekly, or monthly to show trends over time and determine how those trends have affected companies and markets in the past.

Tutorial: Get customer sentiment data for consumer electronics market

Import.io provides both data as a managed service and a hands-on platform. In this example, we are using the Import.io platform to get Samsung consumer sentiment from Amazon.com. 

All you need is one URL to get started!

First we search on Amazon for Samsung products.

Then copy and paste the resulting search URL into Import.io.

Since this is just the first page of products, Import.io can tell that more pages exist and gives you the option to add all of them.

After the data extraction process completes, Import.io allows you to select what data to extract into as many columns as you need.

Import.io extractor where you click on the data you want in each column. You can also separate text into columns using XPath and Regular Expression, for instance to remove the text “out of 5 stars”.

 

We only wanted the product name and ratings info this time and we’ll download those two columns to an Excel spreadsheet.

Import.io Dashboard where you download your data to Excel, CSV, or JSON

 

Now, you have a great spreadsheet of customer sentiment data to then format and integrate into your analysis and reporting process.

Downloaded spreadsheet

 

Since customer sentiment continuously changes, you can schedule this to run every day or even every hour. Import.io also provides an optional Change Report in both PDF and Excel format showing just what has changed in any column of data, or what has been added or removed from the website.

Setting up the Change Report

 

Samsung consumer sentiment Change Report
Samsung consumer sentiment Change Report, sent by email in both PDF and Excel formats

 

So, once you run this extraction, you are set to receive the latest data for tracking sentiment ongoing.

Tracking themes and sentiment would have been impossible without the internet and extremely prohibitive without the ability to continuously extract data into a structured format.

Find out about getting alternative web data for your research project.

Extract data from almost any website


INSTANT ACCESS