Abstract: A recommendation system associated with an online marketplace can generate recommendations pertaining to users and assets of the online marketplace by computing user-asset propensity scores. The recommendation system can compute a corresponding user-asset propensity score for each unique user-asset combination. Based on the scores, recommendations indicating predicted user behavior can be generated. To generate the user-asset propensity scores, the recommendation system can generate machine-learned models based on training data. The model can comprise a plurality of classifiers each being associated with user-asset attributes.

Abstract: A reduced keyboard system (100), with a reduced number of keys (13, 15, 23, 25, 102, 104, 106, 108, 110, 112), but retaining the typing map of the conventional QWERTY or QWERTY-type keyboard by employing an intuitive and learning database engine. A plurality of letters, numerals, symbols and functions are assigned to a set of data keys, buttons or data inputs (multi-character keys). The arrangement of the multi-character keys together with the character assignments to the individual multi-character keys allows a user to use the same typing map, as when typing on a conventional QWERTY or QWERTY-type keyboard, be it visual mapping (i.e. physical location of keys) or finger mapping (i.e. touch typing for typist). This enhances the typing experience on the reduced keyboard system to have the same feeling, typing rhythm and speed as typing on a conventional QWERTY or QWERTY-type keyboard.

Abstract: A method for entering text efficiently by providing letter or word choices. The method includes letter choices to aid inputting accented, diacritic or special characters and a more efficient method to suggest word completion choices including words with accented, diacritic or special characters. This method can be used to enhance any existing text input systems, even reduced keyboard systems. The method also includes a more efficient method to select and input the letter or word choices. This allows for hybrid keyboard systems where physical keys are used in concert with a screen input system to input the letter or word choice.

Abstract: A method for entering text unambiguously. The method includes detecting, on a screen, sensor pad, or reduced keyboard system, a stroke across of an individual character or symbol; and displaying the character or symbol unambiguously. This allows for unambiguous inputting in reduced keyboard systems without the need of changing modes or auxiliary keys.

Abstract: A reduced keyboard system (100), with a reduced number of keys (13, 15, 23, 25, 102, 104, 106, 108, 110, 112), but retaining the typing map of the conventional QWERTY or QWERTY-type keyboard by employing an intuitive and learning database engine. A plurality of letters, numerals, symbols and functions are assigned to a set of data keys, buttons or data inputs (multi-character keys). The arrangement of the multi-character keys together with the character assignments to the individual multi-character keys allows a user to use the same typing map, as when typing on a conventional QWERTY or QWERTY-type keyboard, be it visual mapping (i.e. physical location of keys) or finger mapping (i.e. touch typing for typist). This enhances the typing experience on the reduced keyboard system to have the same feeling, typing rhythm and speed as typing on a conventional QWERTY or QWERTY-type keyboard.