Marketing Insights assignment on the development of an effective marketing plan for the real-estate industry players in Seattle

Question

Task: How to design an effective marketing plan for Seattle using Marketing Insights assignment research methods?

Answer

Question 1
TheMarketing Insights assignment variables which can predict house price in Seattle are indicated below.

• Bedrooms
• Bathrooms
• Sqft living
• Sqft lot
• Floors
• Waterfront
• View
• Condition
• Grade
• Sqft above
• Sqft below
• Year Built
• Year Renovated

One of the key determinants of the house prices identified on this Marketing Insights assignment would be the area of the house. This aspect is captured by variables such as bedrooms, bathroom, Sqft living and Sqft lot. Typically, more the number on each of these variables, it would be expected that house prices would be more assuming the other variables are static. The number of floors also tends to impact the total area of the house and thus the price of the house. Variables such as waterfront and view also tend to impact the price of the house since those with waterfront are preferred more. Also, buyers are willing to pay a premium for houses that have a nice view. The condition and grade variables indicate the overall situation of the house. If the condition and grade of the house are bad, then it would adversely impact the price of the house. Similarly, the variables such as year built and year renovated also act as indicators of the house situation currently and estimate the likely expenses required to renovate.

Question 2
The correlation matrix of the identified Marketing Insights assignmentvariables is indicated as follows.

From the above correlation matrix, it is evident that price of the house has strong positive correlation with sqft living and grade since both these correlation coefficients are positive and exceeds 0.6. Price has moderately strong positive linear association with bathrooms, view, sqft_above since the correlation coefficients for the corresponding variables lie between 0.4 and 0.6 and are positive. Other factors such as condition, year built, year renovated, sqft lot, floors, bedrooms tend to have weak positive linear association with the price.

Question 3
The requisite output from the Marketing Insights assignmentregression analysis is presented as follows.

The slope for the bedrooms variable is negative which implies that more the number of bedroom, lower is the house price. This sounds illogical and may be attributed to the issue of multicollinearity where the bedrooms variable had moderate correlation with bathrooms and sqft living. As expected a lot of the variables have positive slope coefficient since higher values would imply a greater house price. For instance, the slope coefficient of bathrooms is 28032.45 which implies that addition of one bathroom would lead to an average increase of $28,032.45 in the house price assuming that the other independent variables remain constant. Some of the slope coefficients have unexpected signs which may be attributed to the issue of multicollinearity which limits the utility of the given regression model.

Question 4
In order to determine which factors are more important, it needs to be determined which of the slope coefficients are significant assuming a significance level of 1%. Only those slope coefficients would be found significant which have a p value of less than 0.01. Using the Marketing Insights assignmentregression output, the following variables have been found to be significant.

1) Sqft living
2) Waterfront
3) View
4) Grade
5) Sqft_basement
6) Year built

The sqft living is expected to be significant since the price of the house is bound to be influenced by the underlying area. The presence of waterfront is also a significant variable which implies the price increase due to the presence of waterfront is significant. The view variable is also critical when determining price. Another relevant variable is the overall grade. Finally, the amount of area built in basement along with year of construction has been found to be significant with regards to determine the house prices.

Question 5
Some of the other factors identified on this Marketing Insights assignmentwhich have not been provided but could potentially could be useful in determining the house prices are in Seattle are as follows.
1) Distance from CBD (Central Business District) – Typically houses which are situated relatively near to the CBD have a higher price since this tends to reduce the amount of time required to commute to the CBD and thus leads to time & fuel savings. Houses typically tend to be cheaper if located far away from CBD.
2) Distance from the nearest bus/train station – This factor is pivotal since some individuals prefer to have assessable public transport which can save on transportation costs. As a result, the houses which have a nearby bus or train station may have a higher valuation compared to a house which has limited access to public transport.
3) Proximity to certain schools and educational facilities – In some neighbourhood there may be schools and educational organisations which can impact the house prices. This is because proximity to school and universities tend to lower time and money spent in commutation. Also, it is observed on this Marketing Insights assignment that rental income and demand is impacted by proximity to prominent universities which attract international students.