Customer Satisfaction Analysis For AusPaper Company Essay.

Discipline-specific knowledge and capabilities - appropriate to the level of study related to a discipline or profession.

Digital Literacy - Using technologies to find, use and disseminate information

Problem Solving - creating solutions to authentic (real-world and ill-defined) problems.

Apply quantitative reasoning skills to solve complex problems.

Use contemporary data analysis and visualisation tools and recognise the limitation of such tools.

Identifying relevant factors for predicting customer satisfaction

Analyse the relevant dependent variable against other variables included in the dataset. Your job is to decide which variables to include here. Use an appropriate technique to identify important relationships.

The outcome of this task is a list of variables that should be included in the subsequent analysis. Your technical report should describe why some variables were selected while others were dropped from subsequent analyses.

The reputed company, “AusPaper” exports the paper-products to more than 75 countries of Europe, Middle East, Asia, Latin America, Indian subcontinent and Africa. In Australia, “AusPaper” is a well-known subordinate of “Pinnon Paper Industries”.  The products are vended to the customer and through any intermediary also. “Pinnon Paper Industries” has a long history in case of local production of products of paper. In previous years, “AusPaper” generated almost 619000 tonnes of paper products and acquired the local and abroad market of more than 690000 tonnes of “paper-products”. “AusPaper” deals with paper products to the two market sections that are “The newspaper industry” (Herald Sun and Australian Financial Review) and “The magazine industry” (Homes & Gardens and Australian Financial Review).

In recent times, managing authority of “AusPaper” realizes the necessity for ensuring a stationary customer base and absolutely a rigid strategic alliance with the consumers of paper products, magazines and newspapers. Not only is that “AusPaper” preparing to implement an official progression to be able of featuring upcoming financial and accounting turnovers according to the historical data, but also enlarge their business with appropriate direction. Simultaneously, the buyers are being capable of undertaking a premeditated tactics to have a robust strategic corporation with their consumers of Australia and abroad.

Although “AusPaper” has successful operations and firm financial turn-overs over the last twenty years, the company is estimating and predicting about huge transformation within the coming seven years to one decade in the trading surroundings. This transformation results a variation in selections of critically chosen consumer aspects such as habit towards online magazines, choices of readers across newspapers and choice over social media.

The management authority of Australia contributes in an online survey. The questionnaire process involving little amount of questions help to collect data. The collected and tabulated data is convoyed by other accumulated information about the trade. The manageability through the decision support system is incorporated in this way. In this way the data set regarding sales of “AusPaper” warehouse and its trade is tabulated.

With the help of “RealStats” add-ins of MS-Excel the analysis is conducted. The future planning becomes possible with the help of proper planning according the analysis of current and historical data. The apprehensions of “AusPaper” focuses the strategic move of contracted management of firms procuring from “AusPaper”.

The analyst explained his/her ideas from the summarized analysis to comprehend the key research questions. All total 200 samples having 18 variables are included in the “AusPaper” data file.

Digital literacy

The analysis with the support of undertaken variables explain the consumer loyalty and satisfaction with the curriculum of a firm. The facts discover decisive factors that predict consummation of customers alleged from former procurements from “AusPaper”. The analysis targets to prolife detailed perceptions into factors that predict the "likelihood of “AusPaper” customers constructing strategic alliance" with the company. The analyst aims to construct an analytical model to predict the financial turnovers of “AusPaper” in the 2^nd, 3^rd and 4^th quarters of 2017 methodically. For the impending financial year 2017, the analysis would authenticate whether “AusPaper” would be in a sophisticated position or not.

Both nominal and categorical variables are available in this database. The response variable is the expected to be the perception of performance of “AusPaper” on 13 predictors that are measured using a scale with values 0 to 10. 10 is “Excellent” and 0 stands for “Poor”. The other information relevances to involve the trade, customer aspects and business connections. As an example, “image” is the outlook and brand values of "AusPaper" towards the customers.

Descriptive of “Customer satisfaction”:

The customer satisfaction is a numerical variable. Hence, the descriptive statistics is calculated with this data. The average customer satisfaction with past purchases from “AusPaper “is found to be 6.95 (SD = 1.24). Hence, the customer satisfaction level is not low and the spread of customer satisfaction is also within control. It is observed that many of the consumers had highest satisfaction 5.4. The lowest satisfaction level of any consumer is 4.7 and highest satisfaction level of any consumer is 9.9. The satisfaction level hence tabulated as ranging in the interval 5.2.

The median of the satisfaction data set is 7.05. Hence, 50% people are very much satisfied as per survey as their satisfaction rate is more than the median value. Also, 25% of the bottom values of customer satisfaction are less than 6 and 25% of the top values of customer satisfaction are more than 7.9. The distribution tables and charts of customer satisfaction level of rightly and positively skewed. The graphical visualization indicates that the left tail is longer than its right tail of this distribution.

The strategic alliance is a nominal variable. Therefore, frequency table is provide with the data. The frequency table of the variable “Strat_Alliance” that means “Extent to which the customer/respondent perceives his or her firm would engage in strategic alliance/partnership with AusPaper” indicates that among 200 consumers, 114 consumers denied the strategic alliance or strategic partnership with “AusPaper” with the percentage 57%. Conversely, 86 consumers informed that they are involved in strategic alliance or relationship with AusPaper with the percentage share 43%.

Problem solving

The 16 samples are chosen for secondary data analysis in this task. These chosen variables are – “Cstmr_Type”, “Strat_Alliance”, “Prdct_Qual”, “E_Comm”, “Tch_Supp”, “Cmplnt_Supp”, “Advert”, “Prdct_Line”, “Image”, “Pricing”, and “Warranty, New_Prdct ”,“ Billing ”,“ Price_Flex and Delvry_Flex. The analyst choses the variable “Sats” as a dependent variable. Remaining all the variables are assumed to be predictor variables. The dependent variable is a response factor and the independent variables are the explanatory factors. The researcher constructs an advanced predictive model with the single dependent and 15 independent variables. Most of the variables are numerical variables.

First of all, the analyst created a table of correlation coefficient that indicates the negative link of “Pricing” with the customer satisfaction. The variables that have positive significant correlation (r = 0.5 to 1) are –

• Customer Type (r = 0.70722),
• Strategic Alliance (r = 0.692821),
• Delivery Speed (r = 0.630172).
• Complaint Response (r = 0.597566),
• Billing (r = 0.540485)
• Product Quality (r = 0.521052).

The six explanatory variables are significant as per the stepwise regression model. All these six explanatory variables have significant p-values (0.0) below 5%.

Therefore, adjusted R² is the appropriate measure to test association among dependent variables and independent variables and goodness of fitting of the model. The predictive multiple regression model denotes that altogether the 14 factors explain 82.11% variation of the response variable.

The ANOVA table of the multiple regression model helps to find the significance of the overall model with the p-value = 0.05. Therefore, the model is fitted nicely and the factors all together signify the predictive model with 95% confidence. The significant p-values of the independent variables mean that four variables have p-values less than 5%. These six variables are-

• Strat_Alliance (p-value = 0.0000),
• Prdt_Qual (p-value = 0.0000),
• E_Comm (p-value = 0.0000),
• Prdct_Line (p-value = 0.0000)
• Image (p-value = 0.0000)
• Delvry_Speed (p-value = 0.0000).

Therefore, these six variables linearly and significantly associate dependent variable “Sats” among the 15 independent factors with 95% evidence. Rest of all the variables do not have effect on the dependent variable. The reason is that the calculated significant p-values for those variables are greater than 0.05.

The variables that have positive association with predictor variables are “Cstmr_Type”, “Tch_Supp”, “Cmplnt_Res”, “Advert”, “Pricing”, “Warranty”, “New_Prdct”, “Billing” and “Price_Flex”. Rest of the variables have positive link with dependent variable.

The analyst investigates the inherent facts regarding “Product line” of “AusPaper” estimates the variable “Customer Satisfaction” with significance. As per the findings, a previous analysis denoted that the strength of this link may differ with respect to the “customer location”. It means that the customers from global markets have requirements that are more diverse with compare to the specific region such as Australia & New Zealand.

Out of 200 customers, a significant number of 119 customers are the consumers of outside Australia and New Zealand. 81 customers are from Australia and New Zealand. Three multiple regression models are accomplished with the help of four variables which are - “Product line”, “Region”, “Customer satisfaction” and “interaction effect of region and product line”.

Quantitative reasoning

The analysts constructed the first multiple linear regression model assuming “Product line” as explanatory variable and “Customer satisfaction” as response factor. The analyst for the ease of calculation and interception in the regression model converted the variable “Region” into binary variable where “0” shows “Outside ANZ” and “1” shows “ANZ region”. The second multiple linear regression model is constructed with the help of two explanatory variables that are “Region” and “Product line”. The dependent variable is assumed as “Customer satisfaction”. The analyst constructed the third multiple regression model regarding the interaction variable of “Region” and “Product line” as an extra employed explanatory variable. The interaction variable is the multiplication of Region and Product Line. The predictor variables are “Region”, “Product line” and “Interaction effect”. The dependent variable is same as “Customer satisfaction”.

In the first predictive regression model, “product line” has linear, positive and significant association with customer satisfaction with co-efficient 0.608915 and significant p-value = 0.0. That is for 1 unit increase in product line, the customer satisfaction enhances by 0.6 units with 95% probability. In the second predictive regression model, product line and Region both have linear, positive and significant association with response factor “Customer satisfaction”. Product line whose co-efficient is 0.713734 and significant p-value is 0.0 and Region whose co-efficient (-0.54615) and significant p-value is 0.0005. Hence, 1 unit increment in Product line and 1 unit decrement of Region, the response increases by simultaneously 0.71 units and 0.55 units. That indicates, the factors do not have sphericity. In the third multiple regression model, all the three variables Product line, Region and Interaction of these two factors have linear, positive and significant relation with the explanatory factor “Customer satisfaction” where product line has co-efficient is 0.865218 and p-value is 0.0. Here, “Region” has co-efficient 2.927282 and significant p-value is 0.0003 and “Interaction” has co-efficient has (-0.55504) and significant p-value is 0.0. Hence, for 1-unit increment of all the factors, the response variable increases by 0.86 units, 2.93 units and decreases by 0.55 units significantly. Therefore, among the three variables “Product line”, “Region” and the “Interaction effect”, “Product line” and “Region” have linear significant influence on the dependent variable “Customer satisfaction”.

The value of multiple R² (coefficient of determination) is maximum in this first model. Therefore, the model is fitted most nicely. It is a notable fact that the influence of “Region” and “Interaction” effect is not present.  The adjusted multiple R-square is highest in first predictive model. The first regression model has highest “AIC” value and lowset significant p-value among three estimation models. The predictor in this model, product line has less sphericity. Hence, the simple regression model is the most significant model to be fitted well.

Data analysis

The binary logistic regression model assumes “Strategic alliance” as dependent factor and product quality, product line, image, pricing and price flexibility as predictive factors. The logistic model indicates that the predictive factor “Pricing” does not significant association with the response variable “Pricing”. All the other factors are significantly associated with strategic alliance.

The advanced model building proceeds to have the five causes that are “Product Quality”, “Product Line”, “Personnel Image”, “Flexibility” and “Competitive Pricing”. The key objective of the analysis is to fix an advanced predictive regression model utilising key variables that influence the “likelihood of constructing a strategic alliance of partnership” with “AusPaper”.

The logistic regression finds the predicted probabilities of the association of two levels with the association of dichotomous binary variables.

 “Personnel Image” and ‘Product Line” are numerical variables and “Strategic Alliance” is a binary variable having levels 0 and 1. The researcher is eager to find whether personnel image and product line are impanting to the strategic alliance or not significantly. “Personnel Image” and “Product Line” are the independent variables and “Strategic Alliance” is dependent factor in the explanatory logistic regression model. The estimating regression model could be given as-

Both the p-values of two predictor variables in this binary logistic regression model are “Product Line” and “Personnel Image” are 0.0. Here, p-value is less than significance level (5%), the predictor is significant at 5% level of significance. With the calculated probabilities, the Image of “AusPaper” and product line of “AusPaper” predict the estimated probabilities of all the strategic alliance of the consumers.

 “Product Quality” and ‘Price Flexibility” are numerical variables and “Strategic Alliance” is a binary variable with two levels 0 and 1. The analyst is eager to find whether product quality and price flexibility are significantly influencing to the strategic alliance or not.  “Product Quality” and “Price Flexibility” are predictor variables and “Strategic Alliance” is dependent variable in the predictive regression model. The model is shown as-

The calculated p-values of two predictor variables in the binary logistic regression model “Product Quality” and “Price Flexibility” are 0.0. As, calculated p-values are less than significance level (5%), both the predictor variables are significant at significance level 5%. With the calculated probabilities, the “Product quality” of “AusPaper” and “Price flexibility” of “AusPaper” estimate the probabilities of all the strategic alliance.

The forecasting is very natural from the end of an analyst as well as business organisations such as “AusPaper”. The predicted amounts of turnover of the second, third and fourth quarters of 2017 are calculated as $4531.955, $4991.969 and $5043.73. For forecasting the future financial turnover amount, the analyst has undertaken “Time” as predictor variable of quartiles and “Turnover amount ($’000)” as response variable. The factor “Turnover ($’000)” refers for total turnover amount of the time span. The chronological factor “Time” is actually the frequency of quarters starting from 1^st quarter of 2008 to 1^st quarter of 2017.

The average value indicates that consumers of “AusPaper” company are highly satisfied. Many of the consumers are connected strategically. According to the predictive models, the researcher discovered that that mainly four factors “Strategic alliance”, “Product quality”, “E-communication” and “Image” have influence on the level of satisfaction of the customers significantly.

Besides, “Product line”, “Region” and the “Interaction” effect of “Region” and “Product line” has significant relevance to the customer satisfaction of the consumers of “AusPpaer”. “Image” and “Product line” significantly estimate the types of Strategic alliance of “AusPaper” consumers. “Product quality” and “Price flexibility” of “AusPaper” impact the dependent variable “Strategic alliance” of the customers also significantly. The proportion to the “Product Line” and “Personnel Image” to create “Customer Satisfaction” is also proclaimed. The higher values of explanatory factors are enhancing “Customer Satisfaction” and kinds of “Strategic alliance” with “AusPaper” company. The analysis obtains the expected probability of constructing strategic alliance with changing levels of “Product Quality” and “Product Flexibility” in several observations. As an outcome, the quarterly turnover amount of “AusPaper” company also has significantly enhanced. The “AusPaper” is going to be very successful day by day. The quarterly turnover amounts of 2nd, 3rd and 4th quarter are greater in 2017 than any other quartiles of the previous years. Same as first quarter, the turnover amounts of other quarters also have increased accordingly.