Remove 2018 Remove Deep Learning Remove EDA
article thumbnail

Predicting new and existing product sales in semiconductors using Amazon Forecast

AWS Machine Learning Blog

We observed during the exploratory data analysis (EDA) that as we move from micro-level sales (product level) to macro-level sales (BL level), missing values become less significant. For example, in the 2019 WAPE value, we trained our model using sales data between 2011–2018 and predicted sales values for the next 12 months (2019 sale).

article thumbnail

Heartbeat Newsletter: Volume 32

Heartbeat

RoBERTa: A Modified BERT Model for NLP — by Khushboo Kumari An open-source machine learning model called BERT was developed by Google in 2018 for NLP, but this model had some limitations, and due to this, a modified BERT model called RoBERTa (Robustly Optimized BERT Pre-Training Approach) was developed by the team at Facebook in the year 2019.