| 30 | |

| 31 | Level from 1 (beginner) to 5 (professional): 3 |

| 32 | |

| 33 | == More state-of-the-art regression algorithms == |

| 34 | |

| 35 | Find and research state-of-the art regression algorithms found in other packages (R, Weka, ...) and choose the most important representatives not found in Orange. Then reimplement them in Orange. Another option is to add just the wrappers for external libraries if they are open-source and compatible enough. |

| 36 | |

| 37 | Useful skills: Python. Probably also statistics and computation with matrices (numpy). |

| 38 | |

| 39 | Level from 1 (beginner) to 5 (professional): 4 |

| 40 | |

| 41 | == Improve k-Nearest Neighbors == |

| 42 | |

| 43 | For n training and m test examples standard kNN checks the distances to all n training for each test examples. The time complexity is thus O(n*m). |

| 44 | With a smarter implementation this can be improved. |

| 45 | |

| 46 | Useful skills: Python and C. |