### Purpose - ~~Create a model or set of models for Cookd to improve their conversion and retention.~~ - Create a few time series prediction and features importance to help Cookd improve their conversion and retention. Keep in mind this serves as a prototype for future e-commerce products as well. ### Principles - Results - We need to help move the needle with results. Even if it means being a consultant if we can move the needle on conversion we can provide serious value and get paid. - Speed - Finish the modelling in a reasonable time frame and ensure that they get results in a good time. ### Outcome Visioning We are able to understand Google Analytics and provide some value with the data we're able to extract from there. We are able to provide Cookd with some information and data insights through which they're able to improve their conversion and retention. ### Brainstorming - What do I already know about this project? - I have some understanding of how data is structured in Google Analytics - I know how to work with Prophet and time series predictions. I have the API set up for it as well. - I have a broad idea of how I'm going to go about it and what strategies I might apply to dive deeper into the data. - What don’t I know that I need to find out? - Not sure how effective our models would be for their use case which is an e-commerce product - I have no idea whether the results we have in mind are actually going to be useful for Cookd. - Who can I talk to who might provide insights? - Definitely need to talk to the founders of Cookd once we have something for them. The key is to give them some value before we speak so that they feel more comfortable sharing as well. - What can I read or listen to for relevant ideas? - Nothing as of now. Not until I try and get the first round of stuff going. ### Actions - [x] Understand how data is sent from Google Analytics ✅ 2023-08-06 - [x] Write script to identify what correlates heavily with conversion or what features play a huge role in conversion ✅ 2023-08-06 - [x] Write script to identify what correlates heavily with retention or what features play a huge role in repeat users ✅ 2023-08-06 - [x] Write script to identify what correlates heavily with cart size or what features play a huge role in cart size ✅ 2023-08-06 - [x] Write script to figure out what products are often bought together ✅ 2023-08-06 - [x] Connect our backend to Google Analytics API 📅 2023-08-14 ✅ 2023-08-15 - [x] Build API to query by certain dimensions and metrics based on inputs 📅 2023-08-14 ✅ 2023-08-15 - [x] Create the backend for time series prediction based on the data from GA 📅 2023-08-14 ✅ 2023-08-15 - [x] Connect the backend API to graph UI to show time series graphs 📅 2023-08-15 ✅ 2023-08-16 - [x] Make backend models for feature importance 📅 2023-08-15 ✅ 2023-08-16 - [x] Create feature importance UI component 📅 2023-08-15 ✅ 2023-08-16 - [x] Create GA endpoint for top campaigns 📅 2023-08-16 ✅ 2023-08-17 - [x] Create UI component for top campaigns 📅 2023-08-16 ✅ 2023-08-17 - [x] Connect the backend API to the feature importance UI component 📅 2023-08-15 ✅ 2023-08-16 - [x] Create page for revenue forecast 📅 2023-08-16 ✅ 2023-08-17 - [x] Update Navbar 📅 2023-08-16 ✅ 2023-08-17 - [x] Product page endpoints 📅 2023-08-16 ✅ 2023-08-18 - [x] Product UI Page and connection to backend 📅 2023-08-16 ✅ 2023-08-18 - [x] Handle any time out issues 📅 2023-08-17 ✅ 2023-08-17 - [x] API bug to ensure users throughout period are considered 📅 2023-08-18 ✅ 2023-08-18 - [x] Correlations UI for Cookd 📅 2023-08-18 ✅ 2023-08-21