Slide 1

Slide 1 text

MARC JANSEN / RecSys NYC / April 25, 2018 Data Science for Dinner Building Gousto’s recommendation (eco)system

Slide 2

Slide 2 text

No content

Slide 3

Slide 3 text

Simple model Leading proposition Fueling family life through good food ● You pick your recipes from our menu ● We deliver a box of wholesome ingredients in exact proportions with step-by-step recipe cards ● No planning, no supermarkets, no waste ● Most choice (30 recipes per week) ● Most delivery options ● From £2.98 per portion

Slide 4

Slide 4 text

Exponential growth is fun, but also very challenging. Especially, when you are pushing boundaries in customer propositions at the same time. An exciting journey so far 2018

Slide 5

Slide 5 text

1B meals per week in the UK 70% are home-cooked photo credits by https://kulishana.wordpress.com

Slide 6

Slide 6 text

~40 CTO Head of Data 2 Data Scientists Machine Learning Engineer 5 Engineering Squads + UX/UI Head of Digital Product Head of Engineering Data Scientist jr. Data Engineer GoustoTech & Data Science Q1 ‘17 Q3 ‘17 Q1 ’18 Q2 ’18 sr. Data Engineer jr. Data Scientist H2 ‘18 H2 ‘18

Slide 7

Slide 7 text

Collect Everything Store Everything Expose Everything * * Whilst maintaining data security apps web microservices 3rd party airflow (ETL) amazon Redshift (data warehouse) amazon S3 (data archive) (unified log) data scientists data products business users periscope (analytics and dashboards) Amazon DMS (data migration)

Slide 8

Slide 8 text

Demand Planning Personalised Choice Warehouse Optimisation historic orders data Stock Handling X total orders recipe A 3.4% recipe B 2.8% recipe C 4.1% … onions chicken garlic ... 10,000 8,000 7,000 ... orders routes 10012 10012 10012 10013 10013 ... S001 S004 S020 S005 S013 ... R1 R2 R3 R1 R2 R3 0.8 0.8 0.6 0.6 0.4 0.4 1.0 1.0 1.0 R2 onion R3 beef chicken parsley R1 defaults choosers station picks

Slide 9

Slide 9 text

No content

Slide 10

Slide 10 text

Problem ● Our menus are ‘moving targets’ ● Boxes add implicit choice constraints Result ● Hard to keep performance consistent from menu to menu ● Forked version computationally heavy & complex to tune V0.1 collaborative filtering

Slide 11

Slide 11 text

Ingredients C ooking style Calculating recipe similarity Italian pasta bake French tray bake ● Full recipe ontology ● Jaccard-3 distance metric ● Rank menu against user history

Slide 12

Slide 12 text

Measuring success historic live collaborative + curation content-based mc-precision@k* mc-precision@k ~0.55 ~0.70 ? % bought of top 5 TEST 39% % bought of top 5 CONTROL 25% * menu-conditional precision@k, where k = half of no. recipes on menu

Slide 13

Slide 13 text

DAB (Docker / Airflow / AWS Batch) stack deployment 1 2 3 4

Slide 14

Slide 14 text

Building the recommendation ecosystem Direct Indirect mail web voice subs

Slide 15

Slide 15 text

No content