Mashandisirwo eStatistics muMari
Nhamba dzezviverengero ibazi remasvomhu rinowanzoonekwa serisingachinji uye redzidziso, asi muchokwadi, rine mashandisirwo akawanda muzvikamu zvakasiyana-siyana, kusanganisira mari. Nhamba dzezviverengero dzinoita basa rakakosha mukuongorora data, kuita sarudzo, kufanotaura, uye kugadzirisa njodzi munyika yemari. Chinyorwa chino chichaongorora mamwe mashandisirwo akakosha enhamba dzezviverengero mumari uye kuti data rezviverengero nenzira dzinobatsira sei nyanzvi dzemari kugadzirisa matambudziko nemikana.
1. Kuongorora Data uye Kufanotaura
Imwe yenzira huru dzekushandisa nhamba mumari kuongorora nekufanotaura data. Kugadzirisa data renhoroondo kufanotaura mafambiro eramangwana itsika yakajairika muindasitiri yemari. Semuenzaniso, vanoongorora zvemari vanoshandisa data renhoroondo yemitengo yemasheya kufanotaura mafambiro emitengo yeramangwana. Nzira dzehuwandu hwe ...
Kudzoreredzwa Kwemitsara
Kudzoreredzwa kwemutsara kunoshandiswa kuratidza hukama huripo pakati pezvinhu zvinoshanduka zvakazvimiririra nezvinoenderana. Semuenzaniso, mune zvemari, zvinogona kushandiswa kufanotaura mitengo yemasheya (zvinoshanduka zvichienderana) zvichibva pazvinhu zvakasiyana-siyana zvakaita semitengo yemubereko, inflation, kana zvimwe zviratidzo zvehupfumi (zvinoshanduka zvakazvimiririra). Equation iri nyore yekudzokorora mutsara ndeiyi:
\[ Y = \alpha + \beta X + \epsilon \]
Di mana:
– \( Y \) ndiyo shanduko inoenderana (semuenzaniso, mutengo wemasheya),
– \( X \) ndiyo shanduko yakazvimirira (semuenzaniso, mwero wemubereko),
– \( \alpha \) uye \( \beta \) ndiwo ma parameter emuenzaniso,
– \( \epsilon \) ndiyo yasara kana kuti chikanganiso.
Kuongorora Nguva-Nhevedzano
Kuongorora kweTime-series kunoongorora data nekufamba kwenguva kuti vaone mapatani chaiwo kana mafambiro. Mumari, kuongorora kweTime-series kunoshandiswa kufanotaura mitengo yezvinhu, huwandu hwekutengeserana, uye zviratidzo zvehupfumi. Matekiniki akadai seAuto-Regressive Integrated Moving Average (ARIMA) uye Generalized Autoregressive Conditional Heteroskedasticity (GARCH) anoshandiswa mumamodeli aya.
2. Kutarisira Njodzi
Nhamba dzinoitawo basa rakakosha mukugadzirisa njodzi, maitiro ekuona, kuyera, uye kudzora njodzi dzemari dzingangosangana nekambani kana mudyari. Zvimwe zvishandiso zvenhamba zvinoshandiswa kakawanda mukugadzirisa njodzi zvinosanganisira Value at Risk (VaR), stress testing, uye Monte Carlo analysis.
Value at Risk (VaR)
VaR chiyero chenhamba chinofungidzira kurasikirwa kukuru kweportfolio kana pfuma chaiyo munguva yakatarwa ine chiyero chechivimbo chinozivikanwa. Semuenzaniso, 95% VaR yezuva rimwe chete yemadhora miriyoni imwe zvinoreva kuti pane chivimbo che95% chekuti kurasikirwa kweportfolio hakuzopfuure $1 miriyoni muzuva rimwe chete. VaR inogona kuverengerwa uchishandisa nzira dzekare, nzira dzekuongorora, kana Monte Carlo simulations.
Kushungurudzika Kwayedza
Kuyedzwa kwekushushikana kunosanganisira kutevedzera mamiriro akasiyana-siyana emusika akanyanya kushata kuti uone kuti mamiriro aya angakanganisa sei kukosha kweportfolio. Semuenzaniso, dambudziko remari repasi rose ringakanganisa sei portfolio yekudyara? Nekutevedzera mamiriro ezvinhu aya akaipisisa, masangano emari anogona kugadzirira mukana wekurasikirwa kukuru.
3. Portfolio Diversification
Kusiyanisa mari inzira yekudyara ine chinangwa chekuderedza njodzi nekupa mari muzvinhu zvakasiyana-siyana zvisina hukama. Nhamba dzinobatsira mukusiyana kwemari nekuverenga hukama uye covariance pakati pezvinhu zvakasiyana.
Kubatana uye Kubatana
Kubatana kunoyera simba negwara rehukama hwakatsetseka pakati pezvinhu zviviri. Semuenzaniso, kana chimwe chinhu chinowanzo simuka pamwe chete nechimwe, zvinhu zvinonzi zvine hukama hwakanaka. Kusiyana neizvi, kana chimwe chinhu chikakwira nepo chimwe chichidonha, pane hukama husina kunaka. Kubatana kunotangira pa -1 (perfect negative correlation) kusvika pa +1 (perfect positive correlation). Kuderedza njodzi kuburikidza nekusiyana-siyana kunosanganisira kusarudza zvinhu zvine hukama hwakaderera kana husina kunaka.
Portfolio Yakanaka
Dzidziso yeMarkowitz portfolio, kana kuti Mean-Variance Optimization, inoshandisa nhamba kuona portfolio yakanakisisa nekuwedzera kudzoka uye kuderedza njodzi. Nzira iyi inosanganisira kuverenga avhareji (avhareji kudzoka) uye musiyano (njodzi) weportfolio, pamwe nehukama huripo pakati pezvinhu zvakasiyana-siyana zviri mukati meportfolio.
4. Kuwana Zvikwereti
Nhamba dzinoita basa guru mubhizinesi remabhanga, kunyanya mukukweretesa. Mhando dzenhamba dzinoshandiswa kuongorora kukodzera kwechikwereti chevanhu kana makambani, dzakagadzirwa zvichibva padata rekare uye hunhu hwemukwereti.
Kudzoreredza Kwezvinhu
Imwe nzira inowanzoshandiswa mukuongorora zvikwereti ndeye logistic regression. Iyi modhi inofungidzira mukana wekuti munhu anokwereta arege kubhadhara zvikwereti zvichienderana nezvimwe zvinhu zvakaita senhoroondo yechikwereti, mari yaanowana, uye rudzi rwebasa.
\[ \text{Logit}(P) = \alpha + \beta_1 X_1 + \beta_2 X_2 + \dots + \beta_n X_n \]
Apo \( P \) iri mukana wekuti default ivepo, \( \alpha \) iri intercept, uye \( \beta \) iri regression coefficient.
5. Zvibereko uye Sarudzo
Nhamba dzakakoshawo zvikuru mumitengo yezvinobuda muzvigadzirwa uye mitengo yesarudzo. Black-Scholes Model ndeimwe yemhando dzinozivikanwa zvikuru dzemitengo yesarudzo.
Black-Scholes Model
Iyi modhi inoshandisa zvinhu zvakasiyana-siyana zvinopinda muhuwandu hwezviverengero, kusanganisira kushanduka kwemitengo yezvinhu zviri pasi payo, kuverenga mutengo wepfungwa wesarudzo. Fomura yeBlack-Scholes ndeiyi:
\[ C = S_0 N(d_1) – X e^{-rt} N(d_2) \]
Di mana:
– \( C \) mutengo wesarudzo yekufona,
– \( S_0 \) ndiwo mutengo wezvinhu zviripo iye zvino,
– \( X \) mutengo wekurohwa,
– \(r \) chiyero chemubereko chisina njodzi,
– \(t \) ndiyo nguva yekukura,
– \( N(d) \) ibasa rekugovera zvinhu (cumulative distribution function) rekuparadzira zvinhu kwakajairika,
– \( d_1 \) uye \( d_2 \) mavariable anobva mu model input.
Mhedziso
Kubva pakuongorora data kusvika pakugadzirisa njodzi uye kuvaka portfolio, nhamba dzinoita basa guru mune zvemari. Kushandiswa kwenzira dzehuwandu hwezviverengero kunobatsira nyanzvi dzezvemari mukuongorora zviri nani, kufanotaura, uye kuita sarudzo, zvichiita kuti pave nekuvandudzwa kukuru uye kugadzikana muindasitiri yemari. Zvisinei, zvakakosha kugara uchiziva nezvefungidziro nemiganhu yemhando ipi zvayo yehuwandu hwezviverengero inoshandiswa.
Nekufambira mberi kwetekinoroji uye kuwanikwa kuri kuwedzera kwedata, mashandisirwo ezviverengero mumari acharamba achichinja uye achiramba achioma. Ramba uchidzidza uye uchishandisa zviverengero kuti uite sarudzo dzakanyatsojeka uye dzakarongeka munyika yezvemari inogara ichichinja.
