Automatic listing of items based on user specified parameters

1. A method performed by hardware processing circuitry, the method comprising

providing item information for determining item predictions as training data to a machine learning model;

training the machine learning model with the training data;

filtering historical item listings for items having an equivalent type to a particular item;

determining, based on past depreciation of the items being the equivalent type to the particular item, predictions for the particular item with the trained machine learning model, the predictions comprising a plurality of future sales prices over a corresponding plurality of future time periods, the predictions further including a corresponding plurality of different probabilities at different future time periods of the plurality of future time periods of sale completion associated with each of the plurality of future sales prices such that each future sales price of the plurality of future sales prices has a sales probability of sale completion for a time period within the plurality of future time periods;

causing display of a user interface, the user interface configured to display a plurality of controls, each control selectable to define different rules for setting a sales price of the particular item, one of the controls selectable to define a rule setting a variable sales price so as to maintain a fixed probability of sale completion of the item over time based on the predictions such that the variable sales price varies over time in order to maintain the fixed probability over time;

receiving input selecting one of the plurality of controls;

determining a time to initiate publication of an online listing for the particular item; and

automatically publishing the online listing for the particular item in an online listing system in accordance with the determined time.

2. The method of claim 1 , wherein the publishing of the online listing sets a sales price of the particular item in the online listing according to a rule defined by the selected control.

3. The method of claim 1 , further comprising:

monitoring recent completed item listings to determine a current market value for the particular item;

comparing the current market value to a predicted value from the predictions of future sales prices for a current time period; and

generating an alert if a difference between the current market value and the predicted value meet one or more criterion.

4. The method of claim 3 , wherein generating the alert comprises causing display of a notification user interface, the notification user interface configured to display at least two selectable controls, a first control configured to indicate a sales strategy for the item is to be reviewed upon selection of the first control, and a second control configured to indicate the sales strategy is to be maintained upon selection of the second control.

5. The method of claim 1 , wherein the determining of the predictions comprises interval estimation.

6. The method of claim 5 , wherein the determining of the predictions comprises determining one or more of confidence intervals, credible intervals, tolerance intervals, prediction intervals, or likelihood intervals.

7. A system comprising:

hardware processing circuitry;

a hardware memory storing instructions that when executed configure the hardware processing circuitry to perform operations comprising:

providing item information for determining item predictions as training data to a machine learning model;

training the machine learning model with the training data;

filtering historical item listings for items having an equivalent type to a particular item;

determining, based on past depreciation of the items being the equivalent type to the particular item, predictions for the particular item with the trained machine learning model, the predictions comprising a plurality of future sales prices over a corresponding plurality of future time periods, the predictions further including a corresponding plurality of different probabilities at different future time periods of the plurality of future time periods of sale completion associated with each of the plurality of future sales prices such that each future sales price of the plurality of future sales prices has a sales probability of sale completion for a time period within the plurality of future time periods;

causing display of a user interface, the user interface configured to display a plurality of controls, each control selectable to define different rules for setting a sales price of the particular item, one of the controls selectable to define a rule setting a variable sales price so as to maintain a fixed probability of sale completion of the item over time based on the predictions such that the variable sales price varies over time in order to maintain the fixed probability over time;

receiving input selecting one of the plurality of controls;

determining a time to initiate publication of an online listing for the particular item; and

automatically publishing the online listing for the particular item in an online listing system in accordance with the determined time.

8. The system of claim 7 , wherein the publishing of the online listing sets a sales price of the particular item in the online listing according to a rule defined by the selected control.

9. The system of claim 7 , the operations further comprising:

monitoring recent completed item listings to determine a current market value for the particular item;

comparing the current market value to a predicted value from the predictions of future sales prices for a current time period; and

generating an alert if a difference between the current market value and the predicted value meet one or more criterion.

10. The system of claim 9 , wherein generating the alert comprises causing display of a notification user interface, the notification user interface configured to display at least two selectable controls, a first control configured to indicate a sales strategy for the item is to be reviewed upon selection of the first control, and a second control configured to indicate the sales strategy is to be maintained upon selection of the second control.

11. The system of claim 7 , wherein the determining of the predictions comprises interval estimation.

12. The system of claim 11 , wherein the determining of the predictions comprises determining one or more of confidence intervals, credible intervals, tolerance intervals, prediction intervals, or likelihood intervals.

13. A non-transitory computer readable storage medium comprising instructions that when executed configure hardware processing circuitry to perform operations comprising:

providing item information for determining item predictions as training data to a machine learning model;

training the machine learning model with the training data;

filtering historical item listings for items having an equivalent type to a particular item;

determining, based on past depreciation of the items being the equivalent type to the particular item, predictions for the particular item with the trained machine learning model, the predictions comprising a plurality of future sales prices over a corresponding plurality of future time periods the predictions further including a corresponding plurality of different probabilities at different future time periods of the plurality of future time periods of sale completion associated with each of the plurality of future sales prices such that each future sales price of the plurality of future sales prices has a sales probability of sale completion for a time period within the plurality of future time periods;

causing display of a user interface, the user interface configured to display a plurality of controls, each control selectable to define different rules for setting a sales price of the particular item, one of the controls selectable to define a rule setting a variable sales price so as to maintain a fixed probability of sale completion of the item over time based on the predictions such that the variable sales price varies over time in order to maintain the fixed probability over time;

receiving input selecting one of the plurality of controls;

determining a time to initiate publication of an online listing for the particular item; and

automatically publishing the online listing for the particular item in an online listing system in accordance with the determined time.