Difference between revisions of "ANLY482 AY2017-18T2 Group10 Analysis & Findings: Recommendations"
Jump to navigation
Jump to search
| (8 intermediate revisions by 3 users not shown) | |||
| Line 37: | Line 37: | ||
<!-- Body --> | <!-- Body --> | ||
| − | ==<div style="background: #ffffff; padding: 17px;padding:0.3em; letter-spacing:0.1em; line-height: 0.1em; text-indent: 10px; font-size:17px; text-transform:uppercase; font-weight: light; font-family: 'Century Gothic'; border-left:8px solid #1b96fe; margin-bottom:5px"><font color= #000000><strong> | + | ==<div style="background: #ffffff; padding: 17px;padding:0.3em; letter-spacing:0.1em; line-height: 0.1em; text-indent: 10px; font-size:17px; text-transform:uppercase; font-weight: light; font-family: 'Century Gothic'; border-left:8px solid #1b96fe; margin-bottom:5px"><font color= #000000><strong>Impact of Residential Areas </strong></font></div>== |
| − | Through our Exploratory Data Analysis, we identified that there are 2 main clusters for | + | <div style="margin:0px; padding: 10px; background: #f2f4f4; font-family: Century Gothic, Open Sans, Arial, sans-serif; border-radius: 7px; text-align:left; font-size: 15px"> |
| − | + | Through our Exploratory Data Analysis, we identified that there are 2 main clusters for ABC's outlets. One cluster which has a high proportion of tourists, are those which are located in the city, whereas another cluster has outlets located in more residential areas. ABC can use this analysis by examining the demographics of better performing outlets, which can be used to aid in business decision-making in regards to new outlets or relocation. For example, currently the two highest performing outlets are in more residential areas, ABC could factor the surrounding area into consideration when looking for new locations to open in. </div> <br/> | |
| − | |||
| − | </div><br/> | ||
==<div style="background: #ffffff; padding: 17px;padding:0.3em; letter-spacing:0.1em; line-height: 0.1em; text-indent: 10px; font-size:17px; text-transform:uppercase; font-weight: light; font-family: 'Century Gothic'; border-left:8px solid #1b96fe; margin-bottom:5px"><font color= #000000><strong> Standardise UOM For Stocktaking</strong></font></div>== | ==<div style="background: #ffffff; padding: 17px;padding:0.3em; letter-spacing:0.1em; line-height: 0.1em; text-indent: 10px; font-size:17px; text-transform:uppercase; font-weight: light; font-family: 'Century Gothic'; border-left:8px solid #1b96fe; margin-bottom:5px"><font color= #000000><strong> Standardise UOM For Stocktaking</strong></font></div>== | ||
<div style="margin:0px; padding: 10px; background: #f2f4f4; font-family: Century Gothic, Open Sans, Arial, sans-serif; border-radius: 7px; text-align:left; font-size: 15px"> | <div style="margin:0px; padding: 10px; background: #f2f4f4; font-family: Century Gothic, Open Sans, Arial, sans-serif; border-radius: 7px; text-align:left; font-size: 15px"> | ||
| − | One of the main issues that we discovered was that | + | One of the main issues that we discovered was that there are items where quantity is recorded in the wrong units of measurement. From our understanding, this is because the personnel in charge of the stock take may have their own interpretation of the UOM and thus made an error in recording. We recommend that the stocktaker also record the UOM in which they are recording in addition to the quantity value. This will help eliminate such errors in future as it would highlight errors during data entry and improve the accuracy of inventory data in the future, with the potential for cost savings. |
</div><br/> | </div><br/> | ||
| − | ==<div style="background: #ffffff; padding: 17px;padding:0.3em; letter-spacing:0.1em; line-height: 0.1em; text-indent: 10px; font-size:17px; text-transform:uppercase; font-weight: light; font-family: 'Century Gothic'; border-left:8px solid #1b96fe; margin-bottom:5px"><font color= #000000><strong> | + | ==<div style="background: #ffffff; padding: 17px;padding:0.3em; letter-spacing:0.1em; line-height: 0.1em; text-indent: 10px; font-size:17px; text-transform:uppercase; font-weight: light; font-family: 'Century Gothic'; border-left:8px solid #1b96fe; margin-bottom:5px"><font color= #000000><strong>Customer Count Forecasting</strong></font></div>== |
<div style="margin:0px; padding: 10px; background: #f2f4f4; font-family: Century Gothic, Open Sans, Arial, sans-serif; border-radius: 7px; text-align:left; font-size: 15px"> | <div style="margin:0px; padding: 10px; background: #f2f4f4; font-family: Century Gothic, Open Sans, Arial, sans-serif; border-radius: 7px; text-align:left; font-size: 15px"> | ||
| − | + | From the comparison of both Exponential Smoothing and ARIMA for customer count forecasting, we found that the ARIMA models were on average more suitable and more accurate (lower RMSE, MAPE, MAE) than Exponential Smoothing. ABC Company could thus consider implementing ARIMA in forecasting for future customer counts alongside their own internal forecasting methods. | |
</div> | </div> | ||
<!-- End Body ---> | <!-- End Body ---> | ||
Latest revision as of 15:20, 15 April 2018
Impact of Residential Areas
Through our Exploratory Data Analysis, we identified that there are 2 main clusters for ABC's outlets. One cluster which has a high proportion of tourists, are those which are located in the city, whereas another cluster has outlets located in more residential areas. ABC can use this analysis by examining the demographics of better performing outlets, which can be used to aid in business decision-making in regards to new outlets or relocation. For example, currently the two highest performing outlets are in more residential areas, ABC could factor the surrounding area into consideration when looking for new locations to open in.
Standardise UOM For Stocktaking
One of the main issues that we discovered was that there are items where quantity is recorded in the wrong units of measurement. From our understanding, this is because the personnel in charge of the stock take may have their own interpretation of the UOM and thus made an error in recording. We recommend that the stocktaker also record the UOM in which they are recording in addition to the quantity value. This will help eliminate such errors in future as it would highlight errors during data entry and improve the accuracy of inventory data in the future, with the potential for cost savings.
Customer Count Forecasting
From the comparison of both Exponential Smoothing and ARIMA for customer count forecasting, we found that the ARIMA models were on average more suitable and more accurate (lower RMSE, MAPE, MAE) than Exponential Smoothing. ABC Company could thus consider implementing ARIMA in forecasting for future customer counts alongside their own internal forecasting methods.
