I guess Im randomly asking but does someone know of a way to get back into an Instagram account..? I stupidly forgot my password. I appreciate any tips you can offer me!
@Lennox Roger i really appreciate your reply. I got to the site on google and I'm waiting for the hacking stuff now. Seems to take quite some time so I will reply here later with my results.
Hello friends, I have 1 question: In January 2021, the company has made a sales forecast (excluding promotions). So when calculating 3 indicators: forecast bias , Mean absolute deviation (MAD), Mean absolute percentage error (MAPE), the actual sales data must also remove the promotion factor, right?.
Doing a sales forecast is not the right thing to do. You should be doing a demand forecast instead. Also, measuring the error in percentages (MAD, MAPE or MAE) is incorrect as well. Percentages of error don't matter. Only dollars of error matter. Finally, it is also incorrect to remove the promotion from the historical data. Check out tv.lokad.com/journal/2018/5/31/forecasting-promotions/ Hope it helps, Joannes
@@Lokad But Dollars of error will not increase the forecast accuracy, it will measure the amout of money we put bcz of false forecast, which results in E&O or inventory issue... forecast accuracy is used to measure the accuracy of the forecast... mostly applications uses the past demand to drive the forecast, on which we are using the sales and forecast to measure the accuracy of forecast.. why demand forecast is better than sales forecast and what is the different.( i believe only when management sees the error by Amount then they see it as serious Issue?)
@@PrakashNagaraj1993 Thanks for your follow-up! Since this video was posted, I went into a series of SCM lectures which provide a more end-to-end perspective. If you are interested in getting down the rabbit hole, I suggest to have a look at www.lokad.com/lectures Hope it helps, Cheers, Joannes
Hello friends, I have 2 questions: 1/ Why should we make a demand plan for the product family instead of each SKU?, what are the benefits?. 2/ How will product family be understood?. Thank you. Note: My company has 200 SKUs belonging to 3 brands.
Many companies are still using outdated forecasting methods that dysfunction quite a lot when dealing with erratic data. As sales data at the product-level tends to be quite erratic, those companies fall back on forecasting at the product family instead. However, this is just putting the dust under the rug. This does not address the underlying problem which is the lack of methods to cope with erraticity and sparsity. To understand how 'product family' should be understood from a modern sense, check out tv.lokad.com/journal/2022/2/2/structured-predictive-modeling-for-supply-chain/ (this is what 'parameter sharing' is about). This video is part of a series at www.lokad.com/lectures Hope it helps. Joannes
Whoua amazing video very interesting!
Very informative video. Broadening our understanding of concepts in ways we never thought about them
I guess Im randomly asking but does someone know of a way to get back into an Instagram account..?
I stupidly forgot my password. I appreciate any tips you can offer me!
@Mohammad Maximilian Instablaster :)
@Lennox Roger i really appreciate your reply. I got to the site on google and I'm waiting for the hacking stuff now.
Seems to take quite some time so I will reply here later with my results.
@Lennox Roger It worked and I finally got access to my account again. Im so happy!
Thank you so much, you saved my ass :D
@Mohammad Maximilian You are welcome :)
Hello friends,
I have 1 question: In January 2021, the company has made a sales forecast (excluding promotions). So when calculating 3 indicators: forecast bias , Mean absolute deviation (MAD), Mean absolute percentage error (MAPE), the actual sales data must also remove the promotion factor, right?.
Doing a sales forecast is not the right thing to do. You should be doing a demand forecast instead. Also, measuring the error in percentages (MAD, MAPE or MAE) is incorrect as well. Percentages of error don't matter. Only dollars of error matter. Finally, it is also incorrect to remove the promotion from the historical data. Check out tv.lokad.com/journal/2018/5/31/forecasting-promotions/ Hope it helps, Joannes
@@Lokad But Dollars of error will not increase the forecast accuracy, it will measure the amout of money we put bcz of false forecast, which results in E&O or inventory issue... forecast accuracy is used to measure the accuracy of the forecast... mostly applications uses the past demand to drive the forecast, on which we are using the sales and forecast to measure the accuracy of forecast..
why demand forecast is better than sales forecast and what is the different.( i believe only when management sees the error by Amount then they see it as serious Issue?)
@@PrakashNagaraj1993 Thanks for your follow-up! Since this video was posted, I went into a series of SCM lectures which provide a more end-to-end perspective. If you are interested in getting down the rabbit hole, I suggest to have a look at www.lokad.com/lectures Hope it helps, Cheers, Joannes
Hello friends,
I have 2 questions:
1/ Why should we make a demand plan for the product family instead of each SKU?, what are the benefits?.
2/ How will product family be understood?. Thank you.
Note: My company has 200 SKUs belonging to 3 brands.
Many companies are still using outdated forecasting methods that dysfunction quite a lot when dealing with erratic data. As sales data at the product-level tends to be quite erratic, those companies fall back on forecasting at the product family instead. However, this is just putting the dust under the rug. This does not address the underlying problem which is the lack of methods to cope with erraticity and sparsity. To understand how 'product family' should be understood from a modern sense, check out tv.lokad.com/journal/2022/2/2/structured-predictive-modeling-for-supply-chain/ (this is what 'parameter sharing' is about). This video is part of a series at www.lokad.com/lectures Hope it helps. Joannes