Financial-Forecasting.pdf

FINANCIAL FORECASTING  CONTENT 01 define forecasting 02 identify the different uses of forecasting, determine why forecasting is an essential tool in 03 financial planning; 04 differentiate the various tools used in forecasting; and 05 apply the tools and techniques of f...

FINANCIAL FORECASTING  CONTENT 01 define forecasting 02 identify the different uses of forecasting, determine why forecasting is an essential tool in 03 financial planning; 04 differentiate the various tools used in forecasting; and 05 apply the tools and techniques of forecasting. FORECASTING A financial statement analysis helps individuals understand the past performance of a company. Likewise, it gives an idea of what will become of a company in the future.  USERS OF FORECASTS Top Management Purchasing Manager The purchasing manager uses forecasts to ascertain the volume or The top management uses forecasts as a tool for long-range planning, bulk of materials that should be purchased for a particular period particularly in providing a basis for performance targets, implementing of time to avoid overstocking or understocking of inventories. long-range strategic objectives, and making capital budgeting decisions. Production Manager Marketing Manager The production manager utilizes forecasts to determine the amount of The marketing managers uses forecasts to estimate how much raw materials that will be needed in the production, budget, schedule of sales should be made in particular period of time and to production activities, and inventory levels to maintain in order to avoid promotional and advertising activities for the products. disrupting the production, labor hours, and the schedule of shipments.  FINANCE MANAGER The finance manager uses forecasts to anticipate the funding needed by the company. The finance manager must establish the company's cash inflows and outflows and indicate the exact moment when the company will need additional funding. Human Resource Manager The human resource manager uses forecast to supply the human resource needed in achieving the company's objectives. This person must specify when to hire additional people to support company’s operations.  Company KARYLLE's: Financial Statement EXAMPLE : Analysis and Forecasting Step 2: Ratio Analysis: Step 1: Analyzing Historical Profit Margin: Net Income/Revenue Financials. Year 1: 10M/100M = 10% Company KARYLLE’s financial data Year 2: 12M/120M = 10% over the past three years shows: Year 3: 18M/150M = 12% Revenue : Year 1 : 100M The increasing profit margin suggests improved cost Year 2: 120M efficiency. Year 3 : 150M Revenue Growth Rate: Net Income: Year 1: 10M From Yr 1 to Yr2 : (120M-100M)/100M % =20% Year 2: 12M From Yr 2 to Yr 3: (150M-120M)/120M% =25% Year 3: 18M Revenue Growth is accelerating. Operating Expenses: Year 1: 80M Step 3: Cash Flows Analysis: Year 2: 90M Yr 1: 15M Year 3: 100M Yr 2: 18M Yr 3: 22M  Company KARYLLE's: Financial Statement EXAMPLE : Analysis and Forecasting Step 3: Cash Step 4: Forecasting Future Performance: Step 5: Sensitivity Analysis: Flows Using the trends from the past three years we can *If revenue grows by only 15% Analysis create a projection for the next (Year 4): revenue in Year 4 would be: Revenue Forecast: Assuming a 25% revenue 150M × 1.15 = 172.5M Yr 1: 15M growth, we expect revenue in Yr 4: *Net income with a 12% profit margin Yr 2: 18M 150M × 1.25M = 187.5M would be: 172.5M × 12% = 20.7 M Yr 3: 22M Net Income Forecast: Based on the increasing profit margin, we expect the profit margin to reach 13% in Year 4. Projected Net Income: 187.5M × 13% = 24,375 or 24.38 Operating Expenses Forecast: Assuming growth rate 10% in Operating expenses, Year 4 100M × 1.10 = 110M FORECASTING APPROACHES Two Main Approaches To Forecasting: Qualitative Quantitative QUALITATIVE FORECASTING (OR JUDGMENTAL FORECASTING) 25 These forecasts rely on subjective factors like the decision- maker's intuition, emotions, experiences, and values. While 20 combining qualitative and quantitative methods is often most effective, qualitative forecasting is particularly useful for 15 short-term predictions. It can also enhance projections made using quantitative methods. 10 5 0 Item 1 Item 2 Item 3 Item 4 Item 5 QUALITATIVE FORECASTING METHODS: a. Expert opinions b. Delphi method C. Sales force polling d. Consumer market surveys e. PERT-derived forecasts a. Expert Opinions b. The Delphi Method c. Sales Force Polling are synthesized to create consensus involves experts, decision-makers, staff is a method used by companies to estimate future market forecasts using statistical models, but this assistants, and respondents individually conditions, based on direct feedback from sales professionals, method can be biased due to homogeneity answering questionnaires to predict future ensuring a simple, practical, and easily determined forecast in mentalities and group pressure. events, despite low reliability.  CONSUMER MARKET SURVEY Companies, at times, conduct their own customer or potential customer surveys to accumulate information regarding their purchasing plans. QUANTITATIVE A. TIME SERIES FORECASTS FORECASTING i. Naïve model ii. Moving average iii. Weighted moving average iv. Exponential smoothing v. Trend projections B. Assoociative or causal model Explores cause-and-effect relationships DECOMPOSITION OF A TIME SERIES FORECAST Analyzing a time series means breaking down past data into components and projecting them forward. A time series typically has four components: Trend- refers to the gradual upward or downward movement of data over time. seasonality - a data pattern that repeats itself after a period of weeks, months, or quarters. cycle - is a pattern of the data that occurs every several years. random variations- are blips in the data caused by chance and unusual situation.  NAÏVE MODEL The naïve model is a basic forecasting method that assumes the demand for the next period will be the same as the most recent period's demand. It serves as a benchmark model. Advantages of using the naïve model: 1. It is cheap to develop. 2. It does not require any software or machine. 3. Storing data is simple because all one has to do is keep the previous records. 4. It is very easy to operate because it does not require or use complex mathematical applications. Disadvantages of using naïve model: 1. It does not attempt to explain causal relationships with the forecasted variable. 2. A drastic change in the variable for forecasting is not captured Using the symbol Y't+1, as the forecasted value for the next period and the symbol Yt, as the observed value for this period, then: Y't+1 = Yt.  MOVING AVERAGE The moving average model is a basic time series forecasting method where the forecast is based on the average of data from a set number of periods. The number of periods (n) is chosen to minimize forecasting errors. As new data becomes available, the average is updated using the most recent observations. In this model, all data points are given equal weight. The advantages of the moving average are as follows: 1. It is simple to use. 2. It is easy to understand. Its disadvantages are as follows: 1. It requires numerous records and data. 2. Updating the records and data needed to conduct a forecast is convenient. The following formula is used in finding the moving average of order n, MA(n) for a period of t+1, Where: n = is the number of observations used in the calculation  WEIGHTED MOVING AVERAGE The weighted moving average (WMA) is more powerful and economical than a moving average. It is widely used wherein repeated forecasts require the application of methods like sum-of-the-digits and trend adjustment methods. FORMULA: WMAt+1 = ∑ Wt Dt Where: Wt = weight assigned in a particular period Dt = demand for the period  EXPONENTIAL SMOOTHING -This method uses the weighted moving average technique where more weight is given to the recent data. It is supported by the belief that the future is more dependent on the recent past than on the distant past. Alpha α is used as the smoothing parameter to minimize the error and has a value of 0 to 1. It is adjusted until the minimized mean squared error (MSE) is solved. (If the difference between the actual value and the forecasted value is a positive number, a higher α must be assigned. But if the difference is a negative number, then a lower α must be assigned.) Formula for exponential smoothing is:  Example: THE FOLLOWING ARE DATA ON SALES. For illustrative purposes, a five-period average is used as the initial forecast Y’6 with a smoothing constant of α = 0.70. Note that Y6= 110. Then Y`7 is computed as follows: The same procedure is followed in computing for the predicted values of Y`10 – Y`12 The table below shows a comparison between the actual sales and the predicted sales using the exponential smoothing method.  The formula presented in exponential smoothing is expected to give either positive or negative results between the actual sales and the predicted sales. As the objective is to bring the differences or error to zero, the forecaster may use a higher or lower smoothing constant (α) to adjust the prediction to large fluctuations in the data series. The idea is to select α that minimizes the MSE, which is the average sum of the variations between the historical sales data and the forecasted values for the corresponding periods. Assume all the actual sales values from the previous example but with a different α of 0.60. The result of the change in α is shown in the following table together with the MSE. The example with α= 0.70 shows an MSE of 48.28 as compared with α= 0.60 with an MSE of 44.22. It simply means that using a smoothing constant of 0.60 gives the forecaster a better prediction because of a smaller error. It is worth nothing that trying different values for α is necessary before choosing the best α with the least MSE.  TREND PROJECTIONS This technique fits a trend line to a series of Historical data points and projects the line into the future for medium- to long-range forecasts. This results in a straight line that minimizes the deviations between the observed values and the predicted values. Associative or Causal Models The associative or causal models, particularly linear regression, incorporate the variables or factors that might influence the data being forecasted. Linear Regression The linear regression shows the relationship between two variables: the dependent and the independent variables. Example: Nodel Construction Company renovates old homes in Quezon City. Over time, the companh has found that its peso volume of renovation work is dependent on the Quezon City area payroll. If the local chamber of commerce predicts that the Quezon City area payrol will be 600 million new year, the sales of Nodel may be estimated with the regression equation: Sales (in hundred thousands of) = 1.75 +0.25(6) = 1.75+1.50 = 3.25 STANDARD ERROR OF THE ESTIMATE The forecast for 325,000 for Nodel's sales in the example is called a point estimate of y. The point estimate is really the mean, or expected value, of distribution or possible values of sales. To measure the accuracy of the regression estimates, the standard error of the estimates, Syx, must be solved: This, the standard error of the estimate is P30,600 in sales. Correlation Coefficients for Regression Lines The regression equation is one way of expressing the nature of the relationship between two variables. It shows how one variable relates to the values of and changes in another variable. The equation for r is as follows: THANK YOU