Use cases

Web personalization

Cold start
personalization

Search
personalization

Personalize
content

Personalize
payment options

Find the nearest store
for a customer by IP

Cold start personalization

Cold start personalization

Decrease CAC
Increase CR
Proven commercial effect
Why does it matter?
When a user visits your Internet resource for the first time, you don't know anything about it. You don't have the data to do personalization for it. At the same time, good personalization will allow you to reduce Customer Acquisition Cost and increase Conversion Rate to purchase.
How can you solve this problem?
Enrich your databases with external data with a key IP-address. Use it when you get user's IP address. Based on this data, you will be able to personalise your products for users, which will lead to new sales and increasing retention rate.
How could Upgini help you?
Upgini could enrich your DWH with a rich customer profile by IP address. Use this data for Cold start personalisation.
How to solve a Cold start personalization task with Upgini
  1. Obtain a train dataset with customer IP-address and label. Label is a product id that was clicked by user.
  2. Search for new relevant features for your task: launch FIT method of Upgini and get a list of relevant features from connected data sources.
  3. Make a test enrichment: launch TRANSFORM method of Upgini and enrich your dataset with only new relevant features. This dataset could consists any phone number or any IP-address.
  4. Use Upgini in production: Upgini pushes relevant features for the all IP-addresses to your DWH. You may use this data directly in your DWH.
Try Upgini for cold start personalisation
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

# read labeled data
df = pd.read_csv("cold_start_train_dataset.csv")

from upgini import FeaturesEnricher, SearchKey

# map data
enricher = FeaturesEnricher(
    search_keys={'Date': SearchKey.DATE,
                'IPv4': SearchKey.IP})

# launch fit step
enricher.fit(df[['Date','IPv4']], 
             df['clicked_product_id'])

# launch enrichment step
df_enriched = enricher.transform(df)
Search personalization

Search personalization

Increase sales
Improve UX
Free to test
Case description
Personalized search refers to web search experiences that are tailored specifically to an individual's interests by incorporating information about the individual beyond the specific query provided.
Why does it matter?
Search personalization in online stores helps increase sales by improving the user experience, increasing customer engagement and satisfaction, enhancing business competitiveness and growth.
Why Upgini could help you?
Upgini could provide you new relevant information about the individual. Upgini has proven track record of using connected data source for search personalisation.
How to improve search personalization with Upgini
  1. Obtain train dataset with customer IP-address and target label. Add another customer IDs such phone number, email if you have it. Target label may be a search result id that was clicked or not.
  2. Search for new relevant features for your task: launch FIT method of Upgini and get a list of relevant features from connected data sources.
  3. Make a test enrichment: launch TRANSFORM method of Upgini and enrich any dataset with only new relevant features that was found on FIT step.
  4. Use Upgini in production: Upgini will transfer relevant features for the all IP-addresses, Phone numbers, Emails to your DWH. You may use this data directly in your DWH.
Personalize content

Personalize content

Increase sale
Increase CR
Proven commercial effect
Why does it matter?
Personalization can significantly impact conversion rates. By tailoring product recommendations, offers, and messaging based on clients' behavioral profile, you can increase the probability of users making a purchase or taking a desired action.You probably already have a personalization system. To increase the conversion rate from visiting your site to making a purchase, you may to improve the quality of your personalization system and add new relevant data
How can you solve this problem?
Enrich your DWH with new relevant external data that could improve a quality of your recommendation system.
How could Upgini help you?
Upgini could enrich your DWH with a rich customer profile using IP address, email, or phone number. Use this data to personalize content on your site.
Personalize payment options

Personalize payment options

Increase sales
Improve UX
Free to test
Why does it matter?
Improving your payment options can increase your sales and customer satisfaction. Do not show your clients payment options like BNPL or POS-credit if their bank declines them.
How can you solve this problem?
Use an approval prediction machine learning application to score your customers before checkout.
How could Upgini help you?
Search for new relevant features that could help you predict the approval:
  1. Obtain a training dataset with customer ID and label. Upgini supports the following customer IDs: phone number, IP address, and email. The label should indicate customer approval status.
  2. Search for new relevant features for your training dataset: launch the FIT method of Upgini and receive a list of relevant features from connected data sources.
  3. Make a test enrichment: launch the TRANSFORM method of Upgini and enrich your dataset with only the new relevant features.
  4. Use Upgini in production: Upgini transfers relevant features for all phone numbers, emails, and IP addresses to your DWH. You can use this data directly in your DWH.
Find the nearest store for a customer by IP

Find the nearest store for a customer by IP

Increase sale
Increase CR
Proven commercial effect
Why does it matter?
You can't determine a location for a customer who enters your site for the first time. Therefore, you can't personalize your site automatically, and the user could see items that are not available to them.
These attacks can result in a drop in sales.
How can you solve this problem?
Get the postal code of the user by IP from Upgini. Or enrich your systems with a huge GEO-IP vector and try to determine a user's location by yourself.
How could Upgini help you?
  1. Upgini provides out-of-the-box postal code determination by IP-address.
  2. Upgini provides a huge GEO-IP vector for your DWH.

Make ML&AI models happier
with more relevant data

No credit card required. No time limit on Free plan

Get started
Use cases
Fraud preventionMarketing and CRMDemand forecastProduct managementPersonalizationRisk managementLead scoring
Resources
DocsTutorials & Publications
PricingSell your data
for AI & ML applications
aicpa soc
SOC 2
© 2022-2024 Upgini  ·  Designed in UAE, build worldwide