Cortical.io Case Studies How a large US publisher accelerated the RFP process while gaining key market insights

Edit This Case Study Record

	How a large US publisher accelerated the RFP process while gaining key market insights Cortical.io

How a large US publisher accelerated the RFP process while gaining key market insights

Cortical.io

Technology Category	Analytics & Modeling - Machine Learning Analytics & Modeling - Natural Language Processing (NLP)
Applicable Functions	Sales & Marketing
Use Cases	Automated Disease Diagnosis
Services	Data Science Services
Challenge	The media company, owning more than 40 publications, was receiving approximately 100 requests per week, corresponding to about 5,000 messages per year and double as many attachments. These Requests for Proposals (RFPs) needed to be classified depending on criteria like vertical market or target audience before being directed to the appropriate department. The challenge was that the RFPs were highly unstructured documents, coming in various formats like email body text or attachments in Word or Powerpoint. The extraction targets were very diverse and, in most cases, with very little context to learn from, making it difficult for state-of-art machine learning systems to deliver satisfactory results. Read More
About Customer	The customer is a large US-based media conglomerate that owns more than 40 publications. They work with different agencies to sell advertising spaces and receive approximately 100 requests per week, corresponding to about 5,000 messages per year and double as many attachments. These Requests for Proposals (RFPs) need to be classified depending on criteria like vertical market or target audience before being directed to the appropriate department. The company was looking for a solution to automate this process while maintaining an acceptable level of accuracy. Read More
Solution	The company implemented SemanticPro Extract & Analyze, a solution developed by Cortical.io that automatically extracts, reviews, and analyzes key data from requests with a high level of precision. This solution is able to handle short texts without punctuation even with little to no context, as well as different document types like Word, Excel, or Powerpoint. The solution has been successfully trained to recognize very diverse extraction targets like “Campaign name”, “Client” and “Agency”, as well as very specific vocabulary, like “type of ad products“. Extraction results are seamlessly exported in different formats or databases, as preferred by the user. After the production phase is completed, the company envisions to implement a classification and routing solution to route the inbound emails to the appropriate departments. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Machine Learning

Analytics & Modeling - Natural Language Processing (NLP)

Applicable Functions

Sales & Marketing

Use Cases

Automated Disease Diagnosis

Services

Data Science Services

Challenge

The media company, owning more than 40 publications, was receiving approximately 100 requests per week, corresponding to about 5,000 messages per year and double as many attachments. These Requests for Proposals (RFPs) needed to be classified depending on criteria like vertical market or target audience before being directed to the appropriate department. The challenge was that the RFPs were highly unstructured documents, coming in various formats like email body text or attachments in Word or Powerpoint. The extraction targets were very diverse and, in most cases, with very little context to learn from, making it difficult for state-of-art machine learning systems to deliver satisfactory results.

About Customer

The customer is a large US-based media conglomerate that owns more than 40 publications. They work with different agencies to sell advertising spaces and receive approximately 100 requests per week, corresponding to about 5,000 messages per year and double as many attachments. These Requests for Proposals (RFPs) need to be classified depending on criteria like vertical market or target audience before being directed to the appropriate department. The company was looking for a solution to automate this process while maintaining an acceptable level of accuracy.

Solution

The company implemented SemanticPro Extract & Analyze, a solution developed by Cortical.io that automatically extracts, reviews, and analyzes key data from requests with a high level of precision. This solution is able to handle short texts without punctuation even with little to no context, as well as different document types like Word, Excel, or Powerpoint. The solution has been successfully trained to recognize very diverse extraction targets like “Campaign name”, “Client” and “Agency”, as well as very specific vocabulary, like “type of ad products“. Extraction results are seamlessly exported in different formats or databases, as preferred by the user. After the production phase is completed, the company envisions to implement a classification and routing solution to route the inbound emails to the appropriate departments.

Impact #1	The company was able to respond more timely to requests, an increase in responsiveness that typically leads to a higher deal close rate.
Impact #2	The solution is also delivering critical insights about trends and market shifts which helps the Sales team adapt their product strategy and better assess business risks and opportunities.
Impact #3	The company was able to automatically extract a dozen attributes from RFPs, including due date, size of opportunity, vertical market, campaign timeframe, type of campaign, target audience, what is being targeted, etc.

Impact #1

The company was able to respond more timely to requests, an increase in responsiveness that typically leads to a higher deal close rate.

Impact #2

The solution is also delivering critical insights about trends and market shifts which helps the Sales team adapt their product strategy and better assess business risks and opportunities.

Impact #3

The company was able to automatically extract a dozen attributes from RFPs, including due date, size of opportunity, vertical market, campaign timeframe, type of campaign, target audience, what is being targeted, etc.

Benefit #1	The company was able to automatically extract a dozen attributes from RFPs.
Benefit #2	The solution was able to perform these extractions with an accuracy higher than with other machine learning-based approaches.

Benefit #1

The company was able to automatically extract a dozen attributes from RFPs.

Benefit #2

The solution was able to perform these extractions with an accuracy higher than with other machine learning-based approaches.

Download PDF Version

Overview

How a large US publisher accelerated the RFP process while gaining key market insights

Operational Impact

Quantitative Benefit