Optimising the Media Mix for an Advertisement

MyDataModels

Solutions

Optimising the Media Mix for an Advertisement

The effectiveness of any ad campaign relies on the combination of media chosen and the number of advertisements placed. TADA provides a media marketing mix model that helps a company define the optimal media mix for a product advertisement.

Industry

Marketing

Project Duration and Effort

Three days

Type of Prediction

Regression

Customer Benefits

Get the best repartition of spend allocation that drives the highest Return On Investment.
Optimise how the channels will perform in the future based on their spend allocation.
Obtain a model’s performance with an R2 of 99% representing the model’s predictive power, i.e., almost perfect prediction is available.

Problem to solve

Discovering where and how conversions are happening is essential for measuring the performance of your media channels. Predictive modelling is a data analytics solution that allows a business to assess their marketing budget over various channels. It explains how investments in multiple components contribute to revenue.
With the appropriate media mix model, a business can use its past marketing performance to increase future ROI by optimising the channel’s media budget allocation.

We use a dataset, including the following elements in our tool TADA:

Number of sales,
Investment in TV advertising,
Investment in digital advertising,
Investment in radio advertising,
Investment in newspapers advertising,
Investment in magazines advertising,
Out of home advertising,
Month,
Year,
Day,
Season.

In the fast-evolving digital media spectrum, the conventional techniques applied to investigate marketing’s results are no longer the best. We step on the cusp of a media metamorphosis. Media will become more targeted and personalised. Marketers need to adjust to this fact: to grow their business, they need tools to find the perfect media mix.

Objectives

Measure the impact of advertisement spending across each media channel.
Drive the spend allocation mix to optimise revenue.
Provide an accurate revenue prediction.

This challenge raises the following marketing question:

Can the marketing media mix be fine-tuned to improve ROI?

Solution

Based on the dataset described earlier, we asked TADA to predict the sales figures depending on the media marketing mix. The TADA predictive models result in a 99% R2 and a 3% MAPE. It means that the predictive models are very accurate.

TADA has selected the following four main criteria out of the eleven available in the dataset as being relevant and essential for the prediction, with various relative weights:

The investment in TV advertising, with a weight of 32% in TADA’s decision,
The investment in radio advertising, with a weight of 27% in TADA’s decision,
The investment in digital advertising, with a weight of 27% in TADA’s decision,
The investment in magazine advertising, with a weight of 14% in TADA’s decision.

For this specific campaign, TADA shows that investing in TV advertising is worth it, up to a plateau. It also shows that, in this case, the date chosen for the advertisement does not have a significant impact on the revenue generated.

Customer Benefits

In three days, the advertising team achieved to:

Find the right mix of spend allocation that drives the highest ROI.
With Build an almost perfect model with an R2 of 99% representing the model’s predictive power, an almost ideal prediction is available.

Talk to us on how you can make sense of your data and achieve success.

More use cases

Breast Cancer Prediction for Improved Diagnosis

Breast cancer prediction is a diagnosis tool. Oncologists and medical staff face the challenge of identifying breast cancer as soon as possible. ...

Customer recommendation: key drivers identification

The world of ISPs is highly competitive. Customers trust, above all else, other customers’ recommendations. ...

Retaining Customers: Churn Prediction

Anytime a client cuts ties, you encounter the negative consequence of customer churn. While some churn is a natural component of any company, a vast churn rate can cripple any organization's growth. ...

Boosting Lead Qualification with Prediction

On average, the cost of one lead is $198 in 2020. The better the lead qualification, the higher the chances of closing with the customer and generating revenue from these $198 invested. ...

Estimating your House Listing Price

In 2019, 5.34 million existing private homes changed owners, according to data from the National Association of REALTORS®. 89% of sellers were helped by a real estate agent when trading their home....

Predicting the Selling Price of a Used Car

Sales of used light vehicles in the United States grew to about 40.8 million units in 2019. The same year, the average selling price of used cars came to nearly 21,000 U.S. dollars. ...