Brief to DataPOEM
Being an Omnichannel advertising company, The Premium Apparel brand wants to Understand what marketing activities are causing their sales on the Brand website and the impact of marketing on short-term and long-term sales.
Input Data
Below is the Data we have taken as an input.
1. Digital Media Data: We have taken access to all the advertising platforms used our APIs to fetch the data automatically to avoid any data loss. - Digital Media Data from Company (Facebook, Google Ads, Microsoft, Affiliate marketing, Amazon Ads).
2. Offline Media Data: We have taken the data from
3. Web Analytics Data: We have taken web analytics access i.e google analytics and amazon seller central and used our APIs to fetch the data.
4. Shopify Data: We have fetched the data from the APIS we have built.
5. Macro Economical Factors: Brand Category Search Data.
6. Holiday: US Federal Calender.
7. Offers/Discounts: Offers provided.
8. Product Launches: Activities of the new product launches.
Strategy
We have built 20+ models before finalizing the best model that gives 93% accurate attribution of the marketing channels.
The strategy was to predict the latest 1 month's sales from the available data without exposing the latest sales data to the model but by inputting the marketing spends of each channel.
Output
The client was able to see the real attribution of their marketing spending on the sales.
The client was able to identify what is impacting their marketing on short-term and long-term sales.
The client was able to identify the marketing activities that are not causing their sales and reallocate the budgets to the other positive attribution platforms.
Results
25% savings on the media spend by delivering the same results.
Scenario planning with 10+ hypothesis.
93% Accurate model results.