DS Fun Section

12345678910
Across
  1. 4. The measure of reduction in randomness of the data processed.
  2. 6. A problem faced during collaborative filtering when the item recommended to users or the users itself are new to the system.
  3. 9. A "_____" is applied to filter input data and create a feature matrix.
  4. 10. When data has equal or similar variance in different groups of data points, but part of the same dataset.
Down
  1. 1. The measure of asymmetry of data from the ideal gaussian distribution.
  2. 2. A technique used to check if a model is generalised and can capture the patterns in the data. Also used to check for over-fitting.
  3. 3. Maps words to vectors where words having similar meaning are close by in the vector space.
  4. 5. An existing data point against the expected range of data points.
  5. 7. High model complexity leads to high "_____".
  6. 8. The process of reducing words to its root word form. A technique used widely in natural language processing.