on 04-23-2020 3:57 PM
Hi,
I'm having some issues when running Demand Sensing. The output from Demand Sensing is always matching my consensus demand quantity. I think it's because I have getting the following error message
Not enough data to find weekly pattern in lag 0. Default weights used.
Not enough data to find weekly pattern in lag 1. Default weights used.
Not enough data to find weekly pattern in lag 2. Default weights used.
Not enough data to find weekly pattern in lag 3. Default weights used.
Not enough data to compute daily profiles in lag 0. Default weights used
Not enough data to compute daily profiles in lag 1. Default weights used
Not enough data to compute daily profiles in lag 2. Default weights used
Not enough data to compute daily profiles in lag 3. Default weights used
I have ensured my Main input for forecasting (Requested Qty) has 365 days historical data and my snapshot key figure (Consensus Demand Snapshot) has 52 weeks historical data for Lag 0,1,2 & 3.
Can anyone point me in the right direction of what I could be missing?
Thanks.
Ali
Hi,
I would suggest to load the snapshot key figure data once again and run demand sensing with full mode option. Please let us know if you still face the same issue.
Best Regards,
Lingaiah
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.
Hi Mohammad Ejaz,
Are you using Sensing Downstream signal? if yes then make WMAPE as 5% and run it.
Regards,
Pravin Tikar
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.
Hi ptikar ,
I am not using Downstream sensing signal. I am only using Delivered qty, Requested Qty and Confirmed Qty as Input apart from Consensus Demand and Consensus Demand Snapshot key figures as input. WMAPE i kept below 5% only.
I am getting a warning after running the algorithm in the log which says'
An invalid week of quarter value was foundDoes this warning has anything to do with the issue that sensing is not running the algorithm and copying the consensus demand.
Thanks
Aasif
Hi Appa Rao,
As I told I was also getting same message but it solved.
Share details here. I will help you.
Regards,
Pravin Tikar
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.
Hello Ali,
I also got the same issue but I have resolved it. what is Baseline WMAPE threshold (%) value you used? and second thing make sure your near past data for Downsteam signal KF should be good enough for system to identify the pattern if you are using Downstream signal.
Share screenshots if possible.
Regards,
Pravin tikar
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.
Hi Pravin,
I am also getting the same error .I have kept the WAMPE threshold value very less to 0.01. But still, the Demand Sensing algorithm doesnt work and Consensus Demand is copied to Sensed Demand Qty. Kindly let me know what additional setting is required in this to make it work.
Thanks
Aasif
User | Count |
---|---|
5 | |
2 | |
2 | |
1 | |
1 | |
1 | |
1 | |
1 | |
1 | |
1 |
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.