Upgini • Optimize Promotions with Data Enrichment

Promotions

99% match rate for Postal code worldwide

Proven uplift for your models

Use case description

Promotions are a crucial part of a retailer's sales and marketing mix. They can drive sales and help move inventory. However, to get the most out of them, it's important to develop the ability to predict the effect on sales from a 1% discount for each promotional item.

How Upgini could help with Promotions?

Upgini could improve the quality of your promotions by utilizing new, relevant data. This data can aid you in leveraging knowledge about your customers to create the most effective promotions. Furthermore, it can help predict sales with the highest accuracy before a promotion starts.

How to use Upgini?

Search for new relevant features to predict sales with new promo price on any item:

Obtain a training dataset with store ID, date, postal code of the store, historical prices and sales of each item.
Search for new relevant features for your task: launch FIT method of Upgini and get a list of relevant features from connected data sources.
Make a test enrichment: launch TRANSFORM method of Upgini and enrich your dataset with only new relevant features.
Use Upgini in production: Upgini moves relevant features for the all Phone numbers, Emails and IP-addresses to your DWH. You may use this data directly in your DWH.

Try Upgini to create Promotions

Just copy the code and send it to your analyst to repeat!

Upgini will quickly generate a quality report.Ask your analyst to send it to you to check the result.

Copied

%pip install -Uq  upgini

df=pd.read_csv("sales_historical_dataframe.csv")

from upgini import FeaturesEnricher, SearchKey
from upgini.metadata import CVType

enricher = FeaturesEnricher(
    search_keys={
        "day": SearchKey.DATE,
        "postal_code": SearchKey.POSTAL_CODE,
        "country": SearchKey.COUNTRY
        },
  	cv=CVType.time_series
    )

enricher.fit(df.drop(["num_sales"],axis=1), df.num_sales)

#enrich dataset with new features
df_enriched=enricher.transform(df)

Use Upgini to make best Promotions for your clients

Promotions

Make ML&AI models happier
with more relevant data

Use Upgini to make best Promotions for your clients

Promotions

Make ML&AI models happier with more relevant data

Make ML&AI models happier
with more relevant data