Optimizing Distances Between Suppliers And Retailers By Analysis Of Data
Operations management: Optimizing Distances Between Suppliers And Retailers By Analysis Of Data
- EXECUTIVE SUMMARY………………………………………………………….2
- MANAGERIAL PROBLEM………………………………………………………..2
- STATEMENT OF HYPOTHESES………………………………………………….3
- SUPPORTIVE DATA……………………………………………………………….3
- NULL HYPOTHESES AND ALTERNATE HYPOTHESES……………………...4
- QUANTITATIVE ANALYSIS OF DATA………………………………………….5
- QUALITATIVE ANALYSIS……………………………………………………….7
- DATA COLLECTION……………………………………………………………...8
- CONCLUSION……………………&hell ........
I. EXECUTIVE SUMMARY
As operations management is the process of overseeing and controlling aspects of a business’ operations such as production, optimization of supply chain etc, one of the biggest aspects includes ensuring efficiency and the best possible use of resources while conserving time.
Transportation is an essential part of a business’ operations that deals with supply of goods and services. It is one of the factors of a business that incurs most amount of cost and also occupies time. As a part of an operations’ manager’s duties, it is important to optimize the process of transport and identify not only the best possible routes, but also, take into consideration the distances that need to be traveled. For example; a business that deals with perishable goods would always ensure that its units are placed close to one another in order to save time and prevent the goods from getting spoiled before they reach the retail centre.
In this report, transportation costs will be analyzed vis-a-vis distances, null and alternate hypotheses will be conducted, data will be studied and their findings presented. The purpose of this exercise is to be able to understand the uses of hypotheses and analyses to solve managerial problems.
II. MANAGERIAL PROBLEM
The term ‘problem’ is used to denote a state of dissimilarity between an existing situation and the desired one. Further study of managerial problems have led to the understanding that it is not a mere dissimilarity but actually a discrepancy that must be addressed as a priority by the management.
The primary motive of a business is to be able to ensure that the final product reaches the consumer, and towards its fulfillment transportation is a sine non qua. Any discrepancies in the transportation function will only contribute to lowering the value of the final product, which is guaranteed to cause distress to a business.
Through analysis of average distances, transportation costs and subsequent environmental impact, the problem of optimizing transport in order to retain the value of the product is one that must be treated as high priority by those in charge of controlling operations.
The challenges to transportational logistics is not faced by businesses alone. Government institutions and framework need to address these issues as a part of implementation of policies. For example, National Renewable Laboratory in Netherlands believed the largest obstacle to installation of turbines was transport routing.
III. STATEMENT OF HYPOTHESES
The managerial problem of dealing with transportation and its optimization is not a mono faceted one. It can refer to a number of mutually inclusive problems such as transit optimization, route optimization fuel efficiency, optimal routing, vehicle routing etc. This is further complicated by the very fact that the demand of the product will be greater than single vehicle capacities on single routes.
The problem that will be dealt with hereon is a specific one that deals with optimal routing of multiple vehicles. For the sake of this project, routes within the UAE will be taken to provide us distances and road-maps. Combinations of routes, and number of vehicles will be analysed and referenced for arriving at conclusions.
The specific hypotheses that is proposed to be tested is:
Vehicles using x different routes will be more optimum than vehicles using x/2 routes
IV. SUPPORTIVE DATA
Image 1: Road-map of route providing reference point A
For the sake of this study, we are taking Metropolitan as point A. This is the source point from which the products are required to be transported. As has been discussed above, no transport operation goes only from one point to another.There are multiple destinations that a business needs to ensure its products reach the customers at. Therefore, if at point A, the supplier is located at the Metropolitan, we can imagine that there are three different locations at which the supplier will be required to transport the products to.
Point X: Emirates Towers
Point Y: Grand Hyatt
Point Z: Al Murooj Resorts
The distance between Metropolitan and Emirates towers is 449.7m
The distance between Metropolitan and The Grand Hyatt is 18800m
The distance between Metropolitan and Al Murooj Resorts is 15500m
The distances between the three end-points are
Between X and Y: 7600 metres via the shortest route
Between X and Z: 200 metres
Between Y and Z: 7600 metres via the shortest route
Image 2: Schematic diagram of the reference points
V. NULL HYPOTHESES AND ALTERNATE HYPOTHESES
Statement of null hypothesis: The number of routes employed by the vehicles does not have an optimal effect on the overall productivity of the transport activity.
A null hypothesis refers to a statement that the researcher is usually attempting to disprove, hence the name null. An alternate hypothesis, is usually the opposite of the null hypothesis. In the instant case, the alternate hypothesis is similar to our initial statement of hypothesis. That the number of different routes employed by vehicles have a positive effect on the overall productivity of transport, therefore giving us optimal routes across varying distance and time scales.
VI. QUANTITATIVE ANALYSIS OF DATA
The product is to be transported to points X, Y and Z from point A. The total number of vehicles required to transport the product to each point is different. The number of vehicles to be dispatched from point A will depend upon the quantity to one of the delivery points. The optimum number of routes, vehicles on each route need to be calculated.
Point A to Point X
There are two possible routes between Points A and X.
Route 1: 16100 m via Abu Dhabi Ghweifat International
Route 2: 14500 m via Al Wasl Rd/D92
Two vehicles employing the same route will take the same amount of time to reach the destination, i.e. 13 minutes along route 1 and 18 minutes along route 2.
If two vehicles use route 1, and one vehicle employs route two, the average time taken by them is 14.6 minutes. The distance covered via route 2 is shorter, while route one is faster due to various factors.
In this case, the hypotheses test of whether different combinations of routes is better than the utilization of a single route reveals to us that the average time along the same route is shorter. However, qualitative questions such as efficiency along the same route have not been taken into consideration.
Point A to Point Y
Route 1: 22200 m via Abu Dhabi Ghweifat International at 18 minutes
Route 2: 25600m via Al Khail Road at 21 minutes
Route 3: 20600 m via Al Wasl Rd/D92 at 23 minutes
Three trucks traveling via route 1, would make it at an average of 18 minutes, it being the shortest and most efficient route between the two points. Since point Y is not proximate to either point X or Z, it would not make sense to include it as a transit.
Point A to Point Z
Route 1: 15500 via Abu Dhabi Ghweifat International at 14 minutes
Route 2: 1400 m via Al Wasl Rd/D92 at 18 minutes
The three points to which vehicles have to be dispatched from point A use similar routes. Abu Dhabi Ghweifat International as well as Al Wasl Rd/D92.
The average distance that has to be traveled by each of the trucks is: 5977.77m
Point Y, being the farthest from point A will require the three vehicles carrying its product to be transported first, followed by three to point X and then the three of point Z.
The null hypotheses will now be tested with respect to the number of routes and their impact upon optimum delivery. The distance between A to Z and Z to X is relatively shorter than that of the two points to Z, so it would be possible to divert resources between Z and X from A, by using one of them as a transit.
VI. PEARSON CORRELATION CALCULATIONS
Image 3: Formula Applied
The Pearson Correlation Coefficient is a method applied to analyse the correlation between two sets of values. In the instant case, we are attempting to find the correlation between the number of routes employed and their effect on productivity. However, productivity is a qualitative question, and analysing it along a scale of digits is a process that is not only tiresome, but also inaccurate.
This method calculates an active relationship between two quantities. These quantities are continuous variables. A continuous variable is a quantity that varies over a continuum. An important caveat while utilizing the pearson correlation coefficient is that the quantities must be linear i.e. along a single line of calculations.
Distances give us values X and time denotes values Y; This will help us determine if there is a correlation between the two groups
∑ = 115900
Mean = 16557.143
∑(X - Mx)2 = SSx = 365257142.857
∑ = 125
Mean = 17.857
∑(Y - My)2 = SSy = 74.857
X and Y Combined
N = 7
∑(X - Mx)(Y - My) = 53857.143
r = ∑((X - My)(Y - Mx)) / √((SSx)(SSy))
r = 53857.143 / √((365257142.857)(74.857)) = 0.3257
Meta Numerics (cross-check)
r = 0.3257
VII. CALCULATION OF P VALUE FROM THE PEARSON CORRELATION COEFFICIENT
We have used the Pearson Correlation Coefficient, along with our sample number of combinations at 7 pairs and we have derived the p-value for the hypotheses test
The P-Value is 0.475929. The result is not significant at p < 0.05.
This means that the null hypothesis can be rejected. This proves the alternate hypothesis. Therefore, quantitative analysis proves the idea that has been proposed to use multiple routes to deliver the product as a solution to the managerial problem of transport logistics is one that holds water.
VIII. QUALITATIVE ANALYSIS
While in Managerial Economics we see the importance of qualitative analysis of data using methods such as calculation of standard deviation, median and mode, we find that there are qualitative methods of Research and Analysis that are more helpful in offering solutions to managerial problems.
One such method of qualitative analysis is the use of case-studies. We will conduct a short case-study on one company that is considered to be the best in the world in terms of its transport logistics management. The subject of this case study is Walmart. The rate of turnover of inventory of Walmart is very high, and of the 2.3 million employees of the company, over half a million are employed in their transport department. The streamlining of transport routes and the use of multiple routes simultaneously has actually proven to boost the company’s productivity.
6,000 trucks that run for the company cover distances as much as millions of miles in one year. It is not mere advancement of truck technology that has allowed Wal-Mart to deliver 830 million cases more than in the year 2007. It is in fact, a direct result of route optimization employed by the management that has allowed them to increase productivity by a large margin, while traveling shorter distances.
Let us consider the example that we are using to test the hypotheses in the light of qualitative factors that affect transportation. These include inventory holding capacity, delays due to traffic, contingency, capacities of individual trucks etc.
IX. DATA COLLECTION METHODS
Data collection is the primary step in data analysis, it can be collected from either primary or secondary sources. Primary sources of data include field research, surveys and questionnaires that is collected directly from the sample size.
The shortcomings of collecting primary data are a few. The first being that primary data, given its uncorroborated nature, is usually considered unreliable. It is also highly susceptible to researcher bias, and is often viewed with skepticism as it is easier to manipulate primary data. However, primary data plays a very important role while conducting research that is new, and that has not been done before. It also forms foundation for future research, and acts as a reference point for subsequent findings with respect to the same question.
Secondary data, while is corroborated and is considered reliable, comes with its own set of shortcomings. The data is not unique to the research, and it is assumed that it was collected to answer a different research question than the one it is later adapted to. Datum also has the tendency to become obsolete, and while using secondary data it is important for the researcher to test its relevance at the time that it was collected. Failing which, the integrity of the research becomes compromised, and the findings become irrelevant.
Data analysis is a time-consuming process, but it is important. The shortcoming of quantitative data analysis is that it fails to account for intangible factors that affect any business activity. Taking transport logistics as an example, we find that several factors that affect decision making fail to feature in the quantitative aspect.
X. FINDINGS AND IMPLICATIONS ON STAKEHOLDERS
Transport logistics is gaining popularity as a field of management studies, as transportation costs form the largest share of a business’ operational costs. The handling of transport is important as it determines the value of the product as it reaches the consumers.
For the stakeholders, the managerial problem of transportation translates into an urgent need for optimization of routing and vehicular management. From the case, we have found, that the hypotheses we tested on quantitative data established a correlation between all routes and their optimum time, and a study of the averages provided us both the least and the most time taken. However, the p-value is less than 0.05, which means the null hypotheses can be set aside, proving our alternate hypotheses that there exists a positive correlation between alternate routes and productivity.
Further qualitative analysis provided us with the multitude of factors that affect transportation logistics and the study of Wal-Mart’s successful transportation program gives us a contrasting image. The stakeholders must therefore encourage the management to not be deterred by the quantitative findings, but take into consideration the value added by qualitative study of transportation logistics of successful businesses such as UPS.
Development of the different facets of transport logistics, directly improves the product and service of the business. A consumption driven economy is characterized by transport planning that meets demands every step of the way. Through this study into simple transport route optimization, we hope to highlight the importance of the same, and the necessity of managerial effort towards better planning and efficient utilization of resources. This will also help make the transport operation of a business more environment friendly.
- Funke, C. (n.d.). Transport Logistics: Multi Vehicle Routing [Scholarly project]. In
- S. (2017, May). Optimal Routing and Scheduling in Transportation: Using Genetic Algorithm to Solve Difficult Optimization Problems. Retrieved May 12, 2017, from
- Cotrell, J. (n.d.). Analysis of Transportation and Logistics Challenges Affecting the Deployment of Larger Wind Turbines: Summary of Results. Retrieved from
- Bowersox, D. J. (2014, August 01). The Strategic Benefits of Logistics Alliances. Retrieved May 12, 2017, from
- Walmart's Truck Fleet. (n.d.). Retrieved May 12, 2017, from
- Data Collection Methods. (n.d.). Retrieved May 12, 2017, from
- Data Analysis. (n.d.). Retrieved May 12, 2017,
- Transport Efficiency through Logistics Development: Policy Study. (2017, May 06). Retrieved May 12, 2017,
 Funke, C. (n.d.). Transport Logistics: Multi Vehicle Routing [Scholarly project]. In Https://web.stanford.edu/~pavone/papers/Frazzoli.Pavone.ESC13.pdf.
 S. (2017, May). Optimal Routing and Scheduling in Transportation: Using Genetic Algorithm to Solve Difficult Optimization Problems. Retrieved May 12, 2017, from http://www.iitk.ac.in/
 Bowersox, D. J. (2014, August 01). The Strategic Benefits of Logistics Alliances. Retrieved May 12, 2017, from https://hbr.org/1990/07/the-strategic-benefits-of-logistics-alliances
 Cotrell, J. (n.d.). Analysis of Transportation and Logistics Challenges Affecting the Deployment of Larger Wind Turbines: Summary of Results. Retrieved from http://www.nrel.gov/docs/fy14osti/61063.pdf
 Walmart's Truck Fleet. (n.d.). Retrieved May 12, 2017, from http://corporate.walmart.com/global-responsibility/environment-sustainability/truck-fleet
 Data Collection Methods. (n.d.). Retrieved May 12, 2017, from http://www.statisticshowto.com/data-collection-methods/
 Data Analysis. (n.d.). Retrieved May 12, 2017, from http://learntech.uwe.ac.uk/da/Default.aspx?pageid=1442
 Data Analysis. (n.d.). Retrieved May 12, 2017, from http://www.radford.edu/
 Transport Efficiency through Logistics Development: Policy Study. (2017, May 06). Retrieved May 12, 2017, from https://www.adb.org/