Read the abstract ➤ https://www.conf42.com/Python_2024_Ivan_Popov_speed_accuracy_model_development Other sessions at this event ➤ https://www.conf42.com/python2024 Join Discord ➤ https://discord.gg/DnyHgrC7jC Support our mission ➤ https://www.conf42.com/support Chapters 0:00 intro 0:20 preamble 0:29 data scientist at about & render, london, uk 0:57 today's talk 1:20 the essence of balance: speed vs accuracy 1:33 factors impacting accuracy and speed 2:20 the business impact of speed and accuracy 3:11 real-world examples 4:24 balancing act: speed, accuracy, and cost 6:12 strategic importance of the balance 6:37 how to understand business objectives 7:20 scenarios for ml-models 8:30 optimisation strategies 8:40 training data quality and quantity 9:04 what is a good dataset? 9:18 what is a bad dataset? 9:50 data pre-processing 10:40 how to find inefficiencies in data pre-processing? 11:19 yappi 14:07 most common inefficiencies 16:23 feature selection 17:18 shap values for feature selection 20:03 model selection 21:05 xgboost 22:13 lightgbm 23:02 how to choose the best option 23:19 a quick recap 24:45 thank you for your time!