Ingredients Analysis Quality Evaluation - March 2020 - May 2020
Ingredients parsing and recognition metrics
For each product, the ingredients list is parsed to separate each ingredient. Ingredients that we can match to our multilingual ingredients taxonomy as marked as "known", others as "unknown".
There are different reasons an ingredient can be marked as unknown:
- The input ingredient list is incorrect (mispellings etc.)
- The ingredients list contains other things than ingredients and we have not been able to split it at the right place.
- We have not been able to parse a particular sentence structure or formating (e.g. "a drop of delicious honey with a shower of powder sugar")
- The ingredient is not yet present in our taxonomy (or not with the right synonym or in the right language)
Retrieved on 2020-03-05:
EN - English - UK
known 1702 (8.77%) 104818 (79.85%) unknown 17706 (91.23%) 26448 (20.15%) all 19409 (100.00%) 131266 (100.00%)
Top 10k most scanned products:
known 1012 (20.67%) 19061 (79.38%) unknown 3884 (79.31%) 4952 (20.62%) all 4897 (100.00%) 24013 (100.00%)
DE - German - Germany
known 2139 (5.36%) 363967 (84.75%) unknown 37790 (94.64%) 65503 (15.25%) all 39930 (100.00%) 429470 (100.00%)
Top 10k most scanned products:
known 1435 (14.73%) 69066 (85.53%) unknown 8309 (85.26%) 11689 (14.47%) all 9745 (100.00%) 80755 (100.00%)
ES - Spanish - Spain
known 1970 (4.25%) 176101 (71.95%) unknown 44352 (95.75%) 68659 (28.05%) all 46323 (100.00%) 244760 (100.00%)
Top 10k most scanned products:
known 1262 (10.47%) 48797 (75.99%) unknown 10793 (89.52%) 15417 (24.01%) all 12056 (100.00%) 64214 (100.00%)
FI - Finnish - FI
known 829 (43.96%) 11069 (89.15%) unknown 1056 (55.99%) 1347 (10.85%) all 1886 (100.00%) 12416 (100.00%)
Top 10k most scanned products:
known 566 (61.66%) 3465 (89.07%) unknown 351 (38.24%) 425 (10.93%) all 918 (100.00%) 3890 (100.00%)
FR - French - France
known 3825 (0.85%) 3708820 (83.40%) unknown 446838 (99.15%) 738291 (16.60%) all 450664 (100.00%) 4447111 (100.00%)
Top 10k most scanned products:
known 2208 (22.34%) 184218 (94.52%) unknown 7673 (77.65%) 10686 (5.48%) all 9882 (100.00%) 194904 (100.00%)
IT - Italian - Italy
known 1319 (9.43%) 53345 (74.58%) unknown 12669 (90.56%) 18186 (25.42%) all 13989 (100.00%) 71531 (100.00%)
Top 10k most scanned products:
known 911 (13.11%) 20838 (72.21%) unknown 6039 (86.88%) 8018 (27.79%) all 6951 (100.00%) 28856 (100.00%)
NL - Dutch - The Netherlands
known 1304 (17.03%) 31491 (78.84%) unknown 6353 (82.96%) 8453 (21.16%) all 7658 (100.00%) 39944 (100.00%)
Top 10k most scanned products:
known 755 (24.25%) 8069 (73.71%) unknown 2358 (75.72%) 2878 (26.29%) all 3114 (100.00%) 10947 (100.00%)
PT - Portuguese - Portugal
known 918 (16.05%) 15816 (70.50%) unknown 4800 (83.93%) 6617 (29.50%) all 5719 (100.00%) 22433 (100.00%)
Top 10k most scanned products:
known 578 (19.37%) 6261 (68.40%) unknown 2405 (80.60%) 2892 (31.60%) all 2984 (100.00%) 9153 (100.00%)
Ingredients analysis
For each product, once we have parsed the ingredients list to separate each ingredient and match them to our taxonomy, we can analyze if the products are vegan, vegetarian, without palm oil etc.
To mark a product as non-vegan etc. we only need to find one non-vegan ingredient. But to mark a product as vegan, we need to be sure that we have been able to correctly recognize all ingredients so that we can verify that all of them are vegan.
Retrieved on 2020-03-05:
EN - English - UK
Top 10k most scanned products:
DE - German - Germany
Top 10k most scanned products:
ES - Spanish - Spain
Top 10k most scanned products:
FI - Finnish - FI
Top 10k most scanned products:
FR - French - France
Top 10k most scanned products:
IT - Italian - Italy
Top 10k most scanned products:
NL - Dutch - The Netherlands
Top 10k most scanned products:
PT - Portuguese - Portugal
Top 10k most scanned products: