Calvin
commited on
Commit
•
8a1aceb
1
Parent(s):
8575329
updated readme
Browse files
README.md
CHANGED
|
@@ -1,3 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Offer/Deal Recommender
|
| 2 |
|
| 3 |
To solve this problem, I first broke it down into its simplest form and determined the inputs and outputs. The input is a text string that is meant for a category, brand, or a retailer. The first step is to analyze and process the data. The problem would be simple if we could associate every offer to a category, meaning we join based on offer-brand and brand-category. However, there is a contingency that brands may be associated with different categories. For example, Barilla can fall under the category of red sauce and dry pasta, which works out but can also fall under the category of chips in the data which doesn’t make much sense. I processed the data in the following way.
|
|
|
|
| 1 |
+
title: Fetch App
|
| 2 |
+
sdk: streamlit
|
| 3 |
+
sdk_version: 1.25.0
|
| 4 |
+
app_file: offer_pipeline.py
|
| 5 |
+
|
| 6 |
# Offer/Deal Recommender
|
| 7 |
|
| 8 |
To solve this problem, I first broke it down into its simplest form and determined the inputs and outputs. The input is a text string that is meant for a category, brand, or a retailer. The first step is to analyze and process the data. The problem would be simple if we could associate every offer to a category, meaning we join based on offer-brand and brand-category. However, there is a contingency that brands may be associated with different categories. For example, Barilla can fall under the category of red sauce and dry pasta, which works out but can also fall under the category of chips in the data which doesn’t make much sense. I processed the data in the following way.
|